{
  "data": {
    "a": {
      "slug": "diffbot",
      "name": "Diffbot",
      "vendor": "Diffbot Technologies Corp.",
      "vendorUrl": "https://www.diffbot.com",
      "kind": "http-api",
      "category": "web-scrapers",
      "summary": "Diffbot is a hosted set of web data APIs from Diffbot Technologies Corp. of Menlo Park, California. Its Extract API classifies a page and returns typed JSON, alongside Crawl, Web Search, Natural Language and Knowledge Graph APIs.",
      "url": "https://www.anchorterminal.com/tools/diffbot",
      "markdownUrl": "https://www.anchorterminal.com/tools/diffbot.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/diffbot.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/diffbot.json",
      "dns": "diffbot.grade.anchorterminal.com",
      "repo": "https://github.com/diffbot/diffbot-python",
      "license": "Proprietary service under Diffbot's Terms of Use. The Python client, the TypeScript client and the agent skills are MIT",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://api.diffbot.com/v3",
      "packages": [
        {
          "registry": "pypi",
          "name": "diffbot"
        },
        {
          "registry": "npm",
          "name": "@diffbot/typescript"
        }
      ],
      "auth": "api-key",
      "authNotes": "Self-serve token from the dashboard at app.diffbot.com, sent as the `token` query parameter on Extract and Knowledge Graph calls. The official client sends it as a Bearer header to the Web Search endpoint. Tokens carry no scopes. Child tokens have the same rights as the primary token and can be created in the dashboard on the Plus plan and above, or through support. A changelog entry of 30 June 2025 is titled as adding labels and a disable switch for tokens in the dashboard.",
      "pricing": "freemium",
      "pricingNotes": "Free plan of 10,000 credits a month at 5 requests a minute, with no card, so an agent's owner can start without a contract. Startup is $299 a month for 250,000 credits with overage at $0.001 a credit, Plus $899 for 1,000,000 with overage at $0.0009 and access to Crawl, Enterprise by sales. One extracted page is 1 credit, or 2 through the data centre proxy. Whether a failed extraction uses a credit was not found (https://www.diffbot.com/pricing).",
      "priceSummary": "$1 / 1k pages",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 on the pricing page, the authentication and rate limit docs, the Extract OpenAPI file or the official clients (checked 2026-10-09).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": 9,
        "pypiWeekly": null,
        "asOf": "2026-10-09"
      },
      "docsUrl": "https://www.diffbot.com/docs/",
      "llmsTxt": "https://www.diffbot.com/llms.txt",
      "openapi": "https://www.diffbot.com/openapi/extract.json",
      "capabilities": [
        "web.extract",
        "web.scrape",
        "web.crawl",
        "scraping.proxies",
        "web.search",
        "data.knowledge",
        "data.company"
      ],
      "tags": [
        "hosted",
        "freemium",
        "free-tier",
        "no-card",
        "api-key",
        "openapi",
        "llms-txt",
        "agent-skills",
        "cli",
        "python",
        "typescript",
        "proxies",
        "knowledge-graph",
        "status-page",
        "closed-source"
      ],
      "lastRelease": "2026-10-29",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 56.1,
        "grade": "C",
        "agentReady": false,
        "rank": 854,
        "ranked": true,
        "rankOf": 1520,
        "categoryRank": 23,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 63,
          "maintenance": 77,
          "payments": 40,
          "reliability": 55,
          "schema": 83,
          "security": 21,
          "transparency": 68
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-04"
        },
        "negative": 0,
        "verdict": "Extract returns typed JSON for articles, products, discussions and other page types with no selectors to write, under a public OpenAPI 3.1 contract and a free plan that needs no card. The API token travels in the URL query string, tokens carry no scopes, and no security page, certification or security.txt was found.",
        "bestFor": "Agents that want typed article, product or discussion data from arbitrary pages without writing selectors, and teams that also want the Knowledge Graph.",
        "strengths": [
          "OpenAPI 3.1.0 description of the Extract APIs (version 1.1.0, 13 operations) is published at `/openapi/extract.json` and the reference pages are generated from it",
          "Free plan of 10,000 credits a month with no card, and a public credit table. One extracted page costs 1 credit, or 2 through the data centre proxy",
          "Official Python and TypeScript clients and ten agent skills, all MIT. The Python client reached 3.1.0 on 29 October 2026 with tests on Python 3.9 to 3.13",
          "Dated changelog with an RSS feed going back to 2015, and a `/v3` path for the Extract APIs",
          "The privacy policy of 29 August 2025 names each service provider, among them AWS, Stripe, Intercom and Salesforce, and says all are in the United States"
        ],
        "weaknesses": [
          "The token is sent as the `token` query parameter on Extract and Knowledge Graph calls. It is the only scheme in the OpenAPI file",
          "Child tokens have the same access rights as the primary token, and creating them needs the Plus plan ($899 a month) or a request to support",
          "No security page, certification, bug bounty or security.txt was found on the pages read. The privacy policy says some API calls rely on HTTP without encryption",
          "The status page is a Pingdom report with seven days of uptime per check and no incident notes. Analyze API shows 99.69 per cent for the week to 9 October 2026",
          "The docs give `pip install diffbot-python` and `pnpm add diffbot-typescript`, while the repositories now name the packages `diffbot` and `@diffbot/typescript`",
          "The terms grant Diffbot a perpetual, irrevocable licence to process submitted queries, cap liability at $10, and forbid software that scrapes or crawls the Site or Service. That clause matters before any probe is run"
        ],
        "agentNotes": [
          "Call `GET https://api.diffbot.com/v3/analyze?url=\u003cencoded URL\u003e\u0026token=\u003ctoken\u003e` when the page type is unknown. Use `/v3/article` or `/v3/product` to force one schema",
          "Keep the token out of logs and shared URLs. It sits in the query string, so any proxy or log that records the request URL records the token",
          "Stay under 5 calls a minute on Free, 5 a second on Startup and 25 a second on Plus. On 429 wait at least one second and back off",
          "Check a 200 response for `errorCode`. The official client raises `ExtractionError` when a 200 reports a failed extraction",
          "Set `useProxy=default` only when a site blocks the fetch. A proxied page costs 2 credits against 1",
          "Install `diffbot` from PyPI, not `diffbot-python`, which stopped at 0.3.0"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "C",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 56.1
          }
        ],
        "editorialScores": {
          "ergonomics": 63,
          "maintenance": 77,
          "payments": 40,
          "reliability": 55,
          "schema": 83,
          "security": 21,
          "transparency": 49
        },
        "provenanceScore": 87,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-04",
            "maintenance": "2026-11-04",
            "payments": "2026-11-04",
            "reliability": "2026-11-04",
            "schema": "2026-11-04",
            "security": "2026-11-04",
            "transparency": "2026-11-04"
          },
          "last": "2026-11-04",
          "lastMoved": "2026-11-04",
          "oldest": "2026-11-04",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "python3 -m pip install diffbot",
        "http": "curl --request GET \\\n  --url 'https://api.diffbot.com/v3/analyze?token=\u003cDIFFBOT_TOKEN\u003e\u0026url=https%3A%2F%2Fwww.diffbot.com%2Fdocs%2Fintroduction' \\\n  --header 'accept: application/json'",
        "claudeCode": "/plugin marketplace add diffbot/diffbot-skills\n/plugin install diffbot@diffbot-skills"
      },
      "letme": {
        "capability": "https://letme.dev/web.extract",
        "tool": "https://letme.dev/diffbot"
      },
      "area": "web-data",
      "unitPrices": [
        {
          "item": "Extracted page, Startup overage",
          "unit": "1k-pages",
          "usd": 1,
          "note": "1 credit a page at $0.001 a credit"
        },
        {
          "item": "Extracted page through the data centre proxy, Startup overage",
          "unit": "1k-pages",
          "usd": 2,
          "note": "2 credits a page"
        },
        {
          "item": "Extracted page, Plus overage",
          "unit": "1k-pages",
          "usd": 0.9,
          "note": "1 credit a page at $0.0009 a credit"
        },
        {
          "item": "Startup plan",
          "unit": "month",
          "usd": 299,
          "note": "250,000 credits, 5 requests a second"
        },
        {
          "item": "Plus plan",
          "unit": "month",
          "usd": 899,
          "note": "1,000,000 credits, 25 requests a second, Crawl"
        }
      ],
      "provenance": {
        "legalEntity": "Diffbot Technologies Corp.",
        "domain": "diffbot.com",
        "domainRegistered": "2004-08-14",
        "endpointOnVendorDomain": true,
        "terms": "https://www.diffbot.com/company/terms",
        "privacy": "https://www.diffbot.com/company/privacy",
        "statusPage": "https://status.diffbot.com",
        "changelog": "https://www.diffbot.com/changelog",
        "securityTxt": "none",
        "checked": "2026-10-09",
        "notes": [
          "The Terms of Use name Diffbot Technologies Corp. as operator and cover both the Site and the Service, defined as the service that converts a web page into entities and facts. They are the only terms the site links, carry no date, and are the document that governs the API.",
          "The privacy policy was last updated on 29 August 2025, covers visitors, subscribers and people in the index, and gives the address 333 Ravenswood Ave, Menlo Park, CA 94025.",
          "www.diffbot.com/.well-known/security.txt returned 404. No security or trust page is linked from the home page or footer.",
          "The Extract APIs answer at api.diffbot.com, the Knowledge Graph at kg.diffbot.com, Natural Language at nl.diffbot.com and Web Search at llm.diffbot.com, per the docs and the official client's defaults.",
          "RDAP at Verisign gives a registration date of 2004-08-14 for diffbot.com.",
          "robots.txt on www.diffbot.com allows every path. status.diffbot.com disallows only Alexabot."
        ],
        "score": 87
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/diffbot.json",
      "live": {
        "slug": "diffbot",
        "probe": {
          "target": "https://api.diffbot.com/v3",
          "method": "get",
          "lastAt": "2026-11-11T06:59:34.081090934Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 482,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 99.99,
          "p50ms24h": 430,
          "p95ms24h": 606,
          "samples24h": 244,
          "samples30d": 7731,
          "days": [
            {
              "date": "2026-10-11",
              "probes": 247,
              "ok": 247
            },
            {
              "date": "2026-10-12",
              "probes": 247,
              "ok": 247
            },
            {
              "date": "2026-10-13",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-14",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-15",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-16",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-17",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-18",
              "probes": 256,
              "ok": 256
            },
            {
              "date": "2026-10-19",
              "probes": 255,
              "ok": 255
            },
            {
              "date": "2026-10-20",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-21",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-22",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-23",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-24",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-25",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-10-26",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-27",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-28",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-29",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-30",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-31",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-11-01",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-11-02",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-11-03",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-11-04",
              "probes": 246,
              "ok": 246
            },
            {
              "date": "2026-11-05",
              "probes": 185,
              "ok": 185
            },
            {
              "date": "2026-11-06",
              "probes": 241,
              "ok": 241
            },
            {
              "date": "2026-11-07",
              "probes": 243,
              "ok": 242
            },
            {
              "date": "2026-11-08",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-09",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-10",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-11",
              "probes": 72,
              "ok": 72
            }
          ],
          "since": "2026-10-09T00:00:00Z"
        },
        "vendorStatus": {
          "page": "https://status.diffbot.com",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-11T05:34:38.67017346Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "diffbot/diffbot-python",
            "version": "v3.1.0",
            "released": "2026-10-29",
            "seenAt": "2026-11-11T05:52:26.926315755Z"
          },
          {
            "registry": "npm",
            "name": "@diffbot/typescript",
            "version": "0.3.0",
            "seenAt": "2026-11-11T05:52:26.711760421Z"
          },
          {
            "registry": "pypi",
            "name": "diffbot",
            "version": "3.1.0",
            "released": "2026-10-29",
            "seenAt": "2026-11-11T05:52:26.528418377Z"
          }
        ],
        "githubStars": 126,
        "npmWeekly": 262,
        "pypiWeekly": 40,
        "securityTxt": {
          "url": "https://diffbot.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-10T16:08:56.47107311Z"
        },
        "llmsTxt": {
          "url": "https://www.diffbot.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-10T15:42:54.605046378Z"
        },
        "domain": {
          "domain": "diffbot.com",
          "registered": "2004-08-14",
          "source": "https://rdap.verisign.com/com/v1/domain/diffbot.com",
          "checkedAt": "2026-11-08T15:10:31.346599435Z"
        },
        "pages": [
          {
            "url": "https://www.diffbot.com/changelog",
            "kind": "changelog",
            "status": 304,
            "checkedAt": "2026-11-10T16:38:59.735970083Z",
            "changedAt": "2026-10-30T05:54:43.227180558Z",
            "fingerprint": "aafbed2345a0"
          },
          {
            "url": "https://www.diffbot.com/pricing",
            "kind": "pricing",
            "status": 304,
            "checkedAt": "2026-11-10T16:39:05.883579703Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "86884503041e"
          },
          {
            "url": "https://www.diffbot.com/company/privacy",
            "kind": "privacy",
            "status": 304,
            "checkedAt": "2026-11-10T16:39:02.166601063Z",
            "changedAt": "2026-10-17T23:15:07.243669117Z",
            "fingerprint": "53b83d48cccd"
          },
          {
            "url": "https://www.diffbot.com/company/terms",
            "kind": "terms",
            "status": 304,
            "checkedAt": "2026-11-10T16:39:03.878036368Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "a76686da1f94"
          }
        ],
        "github": {
          "repo": "diffbot/diffbot-python",
          "checkedAt": "2026-11-09T10:19:59.49756267Z",
          "stars": 126,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-10-29T23:08:37Z",
          "openIssues": 0,
          "openPRs": 0,
          "issuesOpened90d": 0,
          "issuesClosed90d": 0,
          "prsMerged90d": 0,
          "ci": {
            "branch": "main",
            "runs": 20,
            "success": 20,
            "failure": 0,
            "other": 0,
            "latest": "success",
            "latestAt": "2026-10-29T23:07:32Z"
          }
        },
        "updatedAt": "2026-11-11T06:59:34.081090934Z"
      },
      "streak": {
        "days": 33,
        "from": "2026-10-09",
        "sinceWatching": true,
        "best": 33
      }
    },
    "answer": "Diffbot scores 56.1 (C) on agent readiness against Nexscope's 46.2 (D), and leads in 6 of 7 scored categories. Nexscope leads on security \u0026 auth.",
    "b": {
      "slug": "nexscope",
      "name": "Nexscope",
      "vendor": "ECOCREATE TECHNOLOGY PTE. LTD.",
      "vendorUrl": "https://www.nexscope.ai",
      "kind": "platform",
      "category": "web-scrapers",
      "summary": "Nexscope is a hosted platform for ecommerce sellers with marketplace product, keyword and competitor data for Amazon, TikTok Shop, Walmart, Temu, 1688 and others, plus AI product images and video, through a web app, REST API and remote MCP server.",
      "url": "https://www.anchorterminal.com/tools/nexscope",
      "markdownUrl": "https://www.anchorterminal.com/tools/nexscope.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nexscope.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nexscope.json",
      "dns": "nexscope.grade.anchorterminal.com",
      "repo": "https://github.com/nexscope-ai/nexscope-ecommerce-api",
      "license": "Proprietary hosted service under the Nexscope terms (last updated 8 October 2026), whose contracting party is ECOCREATE TECHNOLOGY PTE. LTD. of Singapore. The OpenAPI file's licence is 'Proprietary API; use subject to Nexscope Terms'. In github.com/nexscope-ai/nexscope-ecommerce-api only the example clients, validation scripts, tests and workflow are MIT. The API documentation, catalogue, definitions and sample data stay copyright Nexscope",
      "transports": [
        "streamable-http",
        "http"
      ],
      "remoteUrl": "https://api.nexscope.ai/mcp",
      "packages": [],
      "auth": "mixed",
      "authNotes": "The remote MCP server takes OAuth 2.1 (authorisation code with PKCE, scope `mcp:tools`) in clients that support it, or a Nexscope API key as `Authorization: Bearer nk-...`, which the tool pages call a compatibility option. The REST API takes the same key as a Bearer header. A person signs in and creates the key under API Access, API Keys. The full key is shown once, and keys can be expired, disabled or deleted, per the help page's troubleshooting. No key scopes, rotation rule or key-management API were found. Creative API key access needs an active subscription. Trial credits don't enable it. The OAuth metadata on api.nexscope.ai was not read (https://www.nexscope.ai/mcp-map/amazon-search, https://www.nexscope.ai/help/skills-external-access, https://github.com/nexscope-ai/nexscope-ecommerce-api, checked 2026-11-10).",
      "pricing": "paid",
      "pricingNotes": "Credits on a monthly subscription. A Free Trial gives 1,000 credits for 3 days with no card, at 1 API and 1 MCP request a second and 1 concurrent each, with no video API. Starter is $29 a month for 30,000 credits (3 requests a second, 2 concurrent), Growth $55 for 75,000 (5 and 4) and Pro $129 for 150,000 (10 and 8), each half price for the first period, with yearly billing and credits that reset monthly and don't roll over. Pay-as-you-go top-ups buy Data credits only, with no subscription. Each tool has its own credit cost, at least 10 for a Data API call. Amazon Search shows 'from 21 credits per call' and a recent average of 30. Refunds within 7 days if unused, per the terms. The home page listed Growth at $69 on the same day (https://www.nexscope.ai/pricing, https://www.nexscope.ai/mcp-map, https://www.nexscope.ai/terms, checked 2026-11-10).",
      "priceSummary": "$0.001 / credit",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 on the pricing page, the API quickstart, the MCP map, llms.txt, the visible part of the OpenAPI file or the GitHub repository on 2026-11-10. Credits come from a subscription or a Data top-up after a browser sign-in (https://www.nexscope.ai/pricing).",
        "endpoints": []
      },
      "toolCount": 382,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-10"
      },
      "docsUrl": "https://www.nexscope.ai/api-docs",
      "llmsTxt": "https://www.nexscope.ai/llms.txt",
      "openapi": "https://api.nexscope.ai/openapi.json",
      "registryName": "io.github.nexscope/ecommerce",
      "capabilities": [
        "web.extract",
        "shopping.search",
        "shopping.prices",
        "seo.keywords",
        "seo.backlinks",
        "search.serp",
        "image.generate",
        "image.edit",
        "video.generate",
        "video.image-to-video"
      ],
      "tags": [
        "hosted",
        "official",
        "closed-source",
        "mcp",
        "remote-mcp",
        "oauth",
        "api-key",
        "openapi",
        "llms-txt",
        "marketplace",
        "shopping",
        "images",
        "video",
        "credits",
        "subscription",
        "free-trial",
        "no-card",
        "new"
      ],
      "lastRelease": "2026-11-09",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 46.2,
        "grade": "D",
        "agentReady": false,
        "rank": 1191,
        "ranked": true,
        "rankOf": 1520,
        "categoryRank": 28,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 44,
          "maintenance": 65,
          "payments": 35,
          "reliability": 39,
          "schema": 64,
          "security": 41,
          "transparency": 41
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-10"
        },
        "negative": 0,
        "verdict": "An agent can reach Amazon, TikTok Shop, Temu, 1688 and other marketplace data, plus image and video models, on one credit balance through a remote MCP server with OAuth or a REST API with a public OpenAPI file. The connection loads 382 tools at once, and there is no status page, changelog or idempotency key.",
        "bestFor": "Agents that research ecommerce products, competitors, keywords, sourcing and patents across Amazon, TikTok Shop, Walmart, Temu, 1688 and other marketplaces, and that also make listing images and video, on one credit balance.",
        "strengths": [
          "Marketplace product, keyword, competitor and sourcing data across more than ten marketplaces behind one key and one MCP endpoint",
          "OAuth 2.1 with PKCE and a `mcp:tools` scope on the MCP server, or a Bearer key shown once",
          "A public OpenAPI 3.1 file and a GitHub repository with request and response definitions, samples and standard-library clients for every documented API",
          "Per-plan API and MCP request limits published, and a 3-day trial of 1,000 credits with no card",
          "1688 order, payment-link, receipt and cancel calls each need an explicit JSON `true` confirmation field"
        ],
        "weaknesses": [
          "The MCP connection advertises the full catalogue of 382 tools, with no toolsets or read-only subset",
          "No status page, SLA, public changelog or security.txt found",
          "No idempotency keys, and business errors answer HTTP 200 unless a header asks otherwise",
          "The privacy policy states no retention periods and names no hosting, AI or data suppliers",
          "Many Data definitions are field descriptors rather than JSON Schema, and the Amazon Search tool page omits the `keyword` argument its own examples pass"
        ],
        "agentNotes": [
          "Check the outer `code` is 0 before reading `data`, or send `X-Nexscope-Http-Status: semantic` to get HTTP error statuses.",
          "Call an image or video tool once, keep the `taskId`, and poll `nexscope_media_task_result`. A second call bills a second job.",
          "Read the tool's credit cost before a call. Each tool costs at least 10 credits and some cost over 300.",
          "Before you set a 1688 confirmation field to `true`, show the user the preview and get approval.",
          "If the server returns 429 or 503, wait for `Retry-After` when present and back off."
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 46.2
          }
        ],
        "editorialScores": {
          "ergonomics": 44,
          "maintenance": 65,
          "payments": 35,
          "reliability": 39,
          "schema": 64,
          "security": 41,
          "transparency": 33
        },
        "provenanceScore": 48,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-10",
            "maintenance": "2026-11-10",
            "payments": "2026-11-10",
            "reliability": "2026-11-10",
            "schema": "2026-11-10",
            "security": "2026-11-10",
            "transparency": "2026-11-10"
          },
          "last": "2026-11-10",
          "oldest": "2026-11-10",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl --fail-with-body -X POST 'https://api.nexscope.ai/api/skill-api/v1/skills/amazon-search/run' \\\n  -H \"Authorization: Bearer $NEXSCOPE_API_KEY\" \\\n  -H 'Content-Type: application/json' \\\n  -H 'X-Nexscope-Http-Status: semantic' \\\n  -d '{\"keyword\":\"phone case\",\"page\":1}'",
        "config": {
          "mcpServers": {
            "nexscope": {
              "headers": {
                "Authorization": "Bearer YOUR_NEXSCOPE_API_KEY"
              },
              "type": "streamableHttp",
              "url": "https://api.nexscope.ai/mcp"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/web.extract",
        "tool": "https://letme.dev/nexscope"
      },
      "area": "web-data",
      "unitPrices": [
        {
          "item": "Nexscope credit (Starter)",
          "unit": "credit",
          "usd": 0.00097,
          "note": "$29 a month for 30,000 credits, half price in the first month. Credits reset monthly"
        },
        {
          "item": "Nexscope credit (Pro)",
          "unit": "credit",
          "usd": 0.00086,
          "note": "$129 a month for 150,000 credits"
        },
        {
          "item": "Amazon Search tool call (Starter)",
          "unit": "call",
          "usd": 0.029,
          "note": "A recent average of 30 credits, range 16 to 94, per the MCP tool page on 10 November 2026. About 20 results a page"
        },
        {
          "item": "Starter plan",
          "unit": "month",
          "usd": 29,
          "note": "30,000 credits, 3 API and 3 MCP requests a second, 2 concurrent each"
        }
      ],
      "provenance": {
        "legalEntity": "ECOCREATE TECHNOLOGY PTE. LTD.",
        "domain": "nexscope.ai",
        "domainRegistered": "2026-03-04",
        "domainNote": "RDAP (Identity Digital) gives nexscope.ai a registration date of 4 March 2026 through GoDaddy, with the registrant behind Domains By Proxy. The terms and privacy policy name ECOCREATE TECHNOLOGY PTE. LTD., 'a company incorporated in Singapore', with no registration number or street address.",
        "endpointOnVendorDomain": true,
        "terms": "https://www.nexscope.ai/terms",
        "privacy": "https://www.nexscope.ai/privacy",
        "statusPage": "",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-11-10",
        "notes": [
          "The terms (last updated 8 October 2026) name ECOCREATE TECHNOLOGY PTE. LTD. under the laws of Singapore with SIAC arbitration seated in Singapore, cap liability at the amount paid in the six months before a claim, promise no availability, permit the official APIs and MCP integrations within plan limits, forbid bots and scrapers outside them, and give notice of material changes through the service or by email.",
          "The privacy policy (last updated 8 October 2026) names the same company, says uploaded materials are not used to train AI models, names Google Analytics, Microsoft Clarity, Ahrefs Analytics, Google Ads, X advertising and FirstPromoter, lists hosting, storage, AI processing, payment, email, support and authentication providers only by type, gives no retention periods ('this policy does not specify a single deletion deadline for all data') and mentions no DPA.",
          "https://www.nexscope.ai/.well-known/security.txt answered a client error. No status page or changelog is linked from the home page, llms.txt, the API quickstart or the MCP map.",
          "robots.txt on www.nexscope.ai gives `*` and twelve named crawlers, ClaudeBot among them, the same rules and disallows /api/ and /share/. Nothing there was fetched. api.nexscope.ai publishes no robots.txt (/robots.txt answers a JSON login error). Only /openapi.json and one GET to /mcp were sent there, per the batch. The MCP registry's /robots.txt answered a client error.",
          "firstReleased is 2026-08-07, the date on Nexscope's launch post ('Updated Aug 07, 2026', no earlier publication date shown), which names API, MCP and Skills as the ways to connect an agent and 1,000 free starting credits. The API repository dates its snapshot of an already public directory of 225 APIs to 10 September 2026, and the OpenAPI version label is 2026-08-28-public-catalog-v1. The domain dates from 4 March 2026 and the npm `nexscope` skills CLI from 20 March 2026, but neither reaches the API. lastRelease is 2026-11-09, when the 1688 procurement API contracts were synced as released."
        ],
        "score": 48
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/nexscope.json",
      "live": {
        "slug": "nexscope",
        "probe": {
          "target": "https://api.nexscope.ai/mcp",
          "method": "get",
          "lastAt": "2026-11-11T06:59:50.048088824Z",
          "lastOk": true,
          "lastStatus": 405,
          "lastMs": 305,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 271,
          "p95ms24h": 358,
          "samples24h": 43,
          "samples30d": 43,
          "days": [
            {
              "date": "2026-11-11",
              "probes": 43,
              "ok": 43
            }
          ],
          "since": "2026-11-11T02:53:20.057234625Z"
        },
        "githubStars": 18,
        "updatedAt": "2026-11-11T06:59:50.048088824Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-11",
        "sinceWatching": true,
        "best": 0
      }
    },
    "edges": [
      {
        "by": 27,
        "category": "transparency",
        "leads": "diffbot",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "A closed service under undated Terms of Use that cover the Site and the Service, cap liability at $10 and grant Diffbot a perpetual licence to process submitted queries. The clients and skills are MIT (13 of 30). The privacy policy of 29 August 2025 says query history and API calls are stored against the API key and kept no longer than necessary, with no retention period given. The GDPR and data rights page was not read (14 of 30). There is no deprecation policy. The changelog carries dated notices, such as a May 2024 entry announcing a field removal for 30 August 2024, and the terms give 14 days' notice of fee changes (8 of 20). The privacy policy names its service providers one by one, among them AWS, Stripe, Intercom, Salesforce, Slack and Amplitude, and says all are in the United States (14 of 20). All per the 9 October check, not re-read on 4 November. 13 + 14 + 8 + 14 = 49.",
          "b": "The editorial half. The service is closed. The terms (8 October 2026) name ECOCREATE TECHNOLOGY PTE. LTD. under Singapore law with no registration number or address. The repository's MIT licence covers client code only, and the documentation and definitions stay copyright Nexscope. Scrapewise earned 15 for closed terms with MIT side code (15 of 30). The privacy policy (8 October 2026) says uploads are not used to train AI models and that connected selling-partner data is deleted or de-identified when no longer needed, but 'this policy does not specify a single deletion deadline for all data', and no DPA was found. SandBase took 12 with no retention periods (10 of 30). No deprecation policy or dated notices. The terms promise notice of material changes before they take effect where practicable, and the MCP map keeps a legacy v1 beside v2 (3 of 20). Analytics and advertising vendors are named (Google Analytics, Microsoft Clarity, Ahrefs, Google Ads, X, FirstPromoter), but hosting, AI processing and payment providers only by type, with no data locations. The repository's source notes say supplier references 'are presented as Nexscope', so the data suppliers go unnamed except LinkFox Agent for 1688 authorisation (5 of 20). 15+10+3+5 = 33. The provenance half is computed from the provenance block."
        },
        "scores": {
          "a": 68,
          "b": 41
        }
      },
      {
        "by": 20,
        "category": "security",
        "leads": "nexscope",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "One token per account, sent in the URL query string as the documented and only scheme in the OpenAPI file. Tokens are revocable in the dashboard per a June 2025 changelog title, and child tokens exist on Plus and above (20 of 30, less 10 for the secret in the URL, so 10). Child tokens have the same rights as the primary one and there is no read-only mode. The skills limit the agent to the `db` binary through `allowed-tools` (5 of 20). The API returns untrusted web content and no guidance on prompt injection was found (0 of 15). The token details page shows usage activity and an Account API reports usage. No per-call log was found (6 of 15). No security.txt, security page, certification or bug bounty was found on the pages read, and the privacy policy says some API calls rely on HTTP without encryption (0 of 20). Site pages per the 9 October check, not re-read on 4 November. OSV lists no advisory for `diffbot` on PyPI or `@diffbot/typescript` on npm on 4 November. 10 + 5 + 0 + 6 + 0 = 21.",
          "b": "The MCP server takes OAuth 2.1 with PKCE and one scope, `mcp:tools`, per the tool pages, or a Bearer `nk-` API key. Keys are created by a person under API Access, shown once, and can be expired, disabled or deleted, with no scopes or rotation found. The OAuth metadata on api.nexscope.ai wasn't read. No query-string key option was found. Manifold earned 22 with OAuth and hashed keys whose storage it documents (20 of 30). Most tools read. Writes exist (1688 procurement on the user's own buyer account, Amazon Ads entity operations through an owned connection, paid generation jobs), and the 1688 calls need an explicit JSON `true` per action after a preview, with the guide saying to get the user's approval first. Credits cap spend. No read-only key or tool allowlist (12 of 20). Tools return third-party listings, reviews, social posts and web pages, and no prompt-injection guidance was found. Manifold, the closest marketing-data MCP, took 0 (0). The Account credits and Account usage APIs, `costToken` in data responses and credits charged on task results give per-call visibility. No key-level audit was found (9 of 15). security.txt answered a client error. No disclosure policy, bug bounty or certification found (0 of 20). 20+12+0+9+0 = 41."
        },
        "scores": {
          "a": 21,
          "b": 41
        }
      },
      {
        "by": 19,
        "category": "schema",
        "leads": "diffbot",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "The Extract APIs have a public OpenAPI 3.1.0 file, version 1.1.0, with 13 operations, and the reference pages are generated from it. We read that file and one rendered page. The descriptions for Crawl, Knowledge Graph and Web Search were not read (25). llms.txt exists but is a short index with no Markdown twins of the docs pages found (5 of 10). The Analyze API page has sections on when to use it and when not to (17 of 20). Parameters are typed, `url` is the one required field and the file has 15 enums, but `fields` is a comma-separated string and the file defines no shared response schemas (10 of 15). The file carries 24 examples. It documents only 200 and 500, with separate docs pages for 401, 404, 429 and 457 (11 of 15). The path is versioned `/v3` and a dated changelog with RSS runs from 2015 to 15 June 2026 (15). All per the 9 October check, not re-read on 4 November (terms bar automated access to the site). 25 + 5 + 17 + 10 + 11 + 15 = 83.",
          "b": "A public OpenAPI 3.1 file at api.nexscope.ai/openapi.json, about 3.8 MB, linked from the quickstart. Visible request bodies are typed with required fields, patterns, enums and `additionalProperties: false`, but responses are open `data` objects and the components section, with the security scheme and the shared error response, wasn't reached. In the repository 166 of 252 request definitions are field descriptors rather than JSON Schema. The hosted tools/list wasn't read. SoldFetch took 17 with untyped responses and SandBase 22 with components unread (19 of 25). llms.txt on www.nexscope.ai and Markdown references for every API in the repository (10). MCP tool descriptions are one line ('Find Amazon products by keyword and marketplace. Results come back as structured JSON.'), with no when-not-to-use. The repository's references carry long trigger text ('trigger this skill whenever their need involves real-time Amazon search results'), not guidance on when to pick another tool (10 of 20). Tool pages list types, defaults, enums and length limits, but the Amazon Search page marks no argument required and omits the `keyword` its own examples pass, and many limits sit in prose (8 of 15). Every API has a request sample, a response fixture and cURL, JavaScript and Python clients, though most fixtures are labelled historical. Errors are an HTTP table, two named codes (11209, 12001) and a semantic error response whose schema wasn't read. MCP errors aren't documented (10 of 15). Path versioning under /v1, MCP v2 beside a legacy v1, and a dated OpenAPI version label, but no public changelog. SandBase earned 7 on the same pattern (7 of 15). 19+10+10+8+10+7 = 64."
        },
        "scores": {
          "a": 83,
          "b": 64
        }
      },
      {
        "by": 19,
        "category": "ergonomics",
        "leads": "diffbot",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Graded on the REST API, with the skills noted. `mode` limits extraction to one page type, `fields` adds optional fields and `discussion=false` drops comments, but an article response carries both `html` and `text` with no way found to drop either. The skills return Markdown by default (14 of 25). A single-URL call has no pagination. Web Search takes `size` and `maxTokens` and DQL takes `size` per the client. Crawl result paging was not read (10 of 20). Errors are JSON with `errorCode` and `error` and six docs pages. A failed extraction can arrive in a 200, and the 429 text says the site received too many requests when the cause is the caller's plan limit (12 of 20). Extract calls are GET reads and safe to retry. Whether a failed call uses a credit was not found, and there is no idempotency key for creating crawl jobs or custom APIs (12 of 20). Only `url` and `token` are required, with official Python and TypeScript clients and a CLI (15). Docs per the 9 October check, not re-read on 4 November. The Python client 3.1.0 (29 October 2026) adds a `snippet_length` option that maps to the Web Search API's `snippetLength`. 14 + 10 + 12 + 12 + 15 = 63.",
          "b": "Read on the MCP server, with the REST API where a line covers it. The MCP map lists 382 tools and says the category manifests 'narrow metadata for your integration; the MCP connection still advertises the full catalog'. That is more than 30 tools with no toolsets, dynamic loading or read-only subset found (5). Search tools page by `page` (about 20 results), with filters such as marketplace, category node, sort and device per tool, but no general pagination model or field selection, and output size depends on each tool (12 of 20). By default business errors answer HTTP 200 with an outer `code`. The `X-Nexscope-Http-Status: semantic` header maps them to HTTP statuses, the OpenAPI file names codes such as `DATA_IMAGE_DOWNLOAD_FAILED` and `CAPABILITY_BACKEND_UNAVAILABLE` in field text, and MCP errors aren't documented. SandBase earned 16 with typed bridge errors (11 of 20). Data calls only read. No idempotency keys and no readOnlyHint or destructiveHint documented. Async jobs return a `taskId` with a poll tool and a rule not to resubmit, and 1688 order, payment-link, receipt and cancel calls need an explicit JSON `true` confirmation (8 of 20). Few required parameters with defaults on most. No official SDK package, only standard-library clients in the repository for JavaScript and Python, which SoldFetch earned 8 for (8 of 15). 5+12+11+8+8 = 44."
        },
        "scores": {
          "a": 63,
          "b": 44
        }
      },
      {
        "by": 16,
        "category": "reliability",
        "leads": "diffbot",
        "name": "Reliability",
        "reasons": {
          "a": "Graded as a hosted API. status.diffbot.com is a Pingdom public report with 13 checks, among them Analyze API, Article API, Crawlbot and Websearch, with daily uptime for seven days and no incident notes (15 of 20). No 90-day record can be read. In the week to 9 October 2026 Analyze API shows 99.69 per cent, with 2, 11 and 17 minutes down on 4, 5 and 6 October, and Article API 5, 9 and 2 minutes on 5 to 7 October (5 of 30, the line for no readable history). Rate limits are published per plan, 5 calls a minute on Free, 5 a second on Startup and 25 a second on Plus (15). The 429 page says to pause one second and back off. No `Retry-After` header is documented, though the official client reads one (10 of 15). No SLA was found (0). The Extract APIs are at `/v3` with no beta label (10). All per the 9 October check, not re-read on 4 November: Diffbot's terms bar software that scrapes or crawls the Site or Service, so its site and status report weren't fetched. 15 + 5 + 15 + 10 + 0 + 10 = 55.",
          "b": "Hosted lines, graded on the remote MCP server and the REST API at api.nexscope.ai. No status page is linked from the home page, llms.txt, the API quickstart or the MCP map, and none was found (0). With no page there is no incident history to read (5). The pricing page publishes requests a second and concurrency per plan, the same for API and MCP, with 1 and 1 on the trial, 3 and 2 on Starter, 5 and 4 on Growth, 10 and 8 on Pro (15). The quickstart calls 429 an 'execution admission rate limit' and says to honour `Retry-After` on 429 and 503 when present. No idempotency key exists. The repository says 'Do not blindly retry POST requests' and to check whether a task was created before resubmitting, and the MCP tool pages say a reconnecting client should query existing async work rather than resubmit. SoldFetch earned 15 with idempotency keys and SandBase 11 with keys on some writes, so guidance without keys earns 9 (9 of 15). No SLA, and the terms say 'We cannot guarantee the Service will be available at all times' (0). No beta or preview label on the API or the MCP server (10). 0+5+15+9+0+10 = 39."
        },
        "scores": {
          "a": 55,
          "b": 39
        }
      },
      {
        "by": 12,
        "category": "maintenance",
        "leads": "diffbot",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Every dated source of the vendor's own was looked for in its GitHub repositories, since its site wasn't re-read. The official Python client, `diffbot` in the listing's packages, was tagged v3.1.0 on 29 October 2026, adding a Web Search `snippet_length` option, and the agent skills were tagged v1.2.0 the same day with rewritten skill content, 6 days before this check (30; was 10 on the API changelog's 15 June 2026 entry, which is per the 9 October check, not re-read on 4 November). In the 90 days from 6 August, the skills were tagged v1.1.0 (12 August, five new skills), v1.1.1 (13 August, a plugin marketplace manifest, counted half) and v1.2.0, and the Python client v3.0.0 (28 September) and v3.1.0, counted half as SDK tags, 3.5 in all (20). A public changelog with RSS and a support address exist. GitHub issues were not read (8 of 15 for a closed service). Python and TypeScript clients exist, but the docs named the packages `diffbot-python` and `diffbot-typescript` on 9 October while the repositories publish `diffbot` and `@diffbot/typescript`, and the TypeScript repository has no tag and no commit since 17 August 2026 (12 of 15). The Python repository tests on Python 3.9 to 3.13. We did not see CI results (7 of 10). 30 + 20 + 8 + 12 + 7 = 77.",
          "b": "Read as a closed service with a public documentation repository. The repository synced the released 1688 procurement contracts on 9 November 2026 and committed again on 10 November (30). No releases or changelog. The dated record is the registry's four versions on 14 and 16 October, repository commits on 8, 9, 20 and 29 October and 2, 9 and 10 November, and source notes dating WooCommerce (29 October) and design search (2 November) additions. SoldFetch earned 10 for dated commits without releases (10 of 20). No public changelog. Support is service@nexscope.ai, WhatsApp and a booked call, untested. The repository's one merged pull request came from the organisation itself, and GitHub's API refused us, so issues weren't read (5 of 15). The official MCP registry lists `io.github.nexscope/ecommerce`, active, latest 1.0.3 of 16 October 2026, read first-hand (15). A CI workflow runs offline catalogue validation and unit tests on standard-library clients with no dependencies. The run results weren't read (5 of 10). 30+10+5+15+5 = 65."
        },
        "scores": {
          "a": 77,
          "b": 65
        }
      }
    ],
    "facts": [
      {
        "a": "HTTP API",
        "b": "Platform",
        "name": "Kind"
      },
      {
        "a": "Diffbot Technologies Corp.",
        "b": "ECOCREATE TECHNOLOGY PTE. LTD.",
        "name": "Vendor"
      },
      {
        "a": "https://api.diffbot.com/v3",
        "b": "https://api.nexscope.ai/mcp",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "Streamable HTTP, HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Paid",
        "name": "Pricing"
      },
      {
        "a": "$0.90 per 1,000 pages",
        "b": "not published",
        "name": "Price for extraction"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Proprietary service under Diffbot's Terms of Use. The Python client, the TypeScript client and the agent skills are MIT",
        "b": "Proprietary hosted service under the Nexscope terms (last updated 8 October 2026), whose contracting party is ECOCREATE TECHNOLOGY PTE. LTD. of Singapore. The OpenAPI file's licence is 'Proprietary API; use subject to Nexscope Terms'. In github.com/nexscope-ai/nexscope-ecommerce-api only the example clients, validation scripts, tests and workflow are MIT. The API documentation, catalogue, definitions and sample data stay copyright Nexscope",
        "name": "Licence"
      },
      {
        "a": "none",
        "b": "382",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "not listed",
        "b": "io.github.nexscope/ecommerce",
        "name": "MCP registry"
      },
      {
        "a": "2026-10-29",
        "b": "2026-11-09",
        "name": "Last release"
      },
      {
        "a": "no date given",
        "b": "not read yet",
        "name": "Terms last updated"
      },
      {
        "a": "2025-08-29",
        "b": "not read yet",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Customer content may train models"
      },
      {
        "a": "yes",
        "b": "not read yet",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "yes",
        "b": "not read yet",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "9 npm/wk",
        "b": "none",
        "name": "Popularity"
      }
    ],
    "faq": [
      {
        "answer": "Diffbot scores 56.1 (C) on agent readiness against Nexscope's 46.2 (D), and leads in 6 of 7 scored categories. Nexscope leads on security \u0026 auth.",
        "question": "Which is better for AI agents, Diffbot or Nexscope?"
      },
      {
        "answer": "Yes. Diffbot has a hosted endpoint at https://api.diffbot.com/v3 and Nexscope at https://api.nexscope.ai/mcp.",
        "question": "Can an agent call Diffbot and Nexscope without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 55 against 39",
          "Schema \u0026 documentation, 83 against 64",
          "Agent ergonomics, 63 against 44",
          "Payments \u0026 pricing, 40 against 35",
          "Maintenance \u0026 community, 77 against 65",
          "Transparency \u0026 trust, 68 against 41"
        ],
        "also": null,
        "goodFor": "Agents that want typed article, product or discussion data from arbitrary pages without writing selectors, and teams that also want the Knowledge Graph.",
        "slug": "diffbot",
        "watchFor": "The token is sent as the `token` query parameter on Extract and Knowledge Graph calls. It is the only scheme in the OpenAPI file"
      },
      {
        "aheadOn": [
          "Security \u0026 auth, 41 against 21"
        ],
        "also": null,
        "goodFor": "Agents that research ecommerce products, competitors, keywords, sourcing and patents across Amazon, TikTok Shop, Walmart, Temu, 1688 and other marketplaces, and that also make listing images and video, on one credit balance.",
        "slug": "nexscope",
        "watchFor": "The MCP connection advertises the full catalogue of 382 tools, with no toolsets or read-only subset"
      }
    ],
    "history": {
      "diffbot": [
        {
          "causes": [
            "product"
          ],
          "date": "2026-11-04",
          "delta": 1.8,
          "from": 54.3,
          "fromGrade": "C",
          "to": 56.1,
          "toGrade": "C"
        }
      ],
      "nexscope": null
    },
    "job": {
      "capability": "web.extract",
      "name": "Extraction"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-diffbot.json",
        "title": "Bright Data vs Diffbot",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-diffbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/browseract-vs-diffbot.json",
        "title": "BrowserAct vs Diffbot",
        "url": "https://www.anchorterminal.com/compare/browseract-vs-diffbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/context-dev-vs-diffbot.json",
        "title": "Context.dev vs Diffbot",
        "url": "https://www.anchorterminal.com/compare/context-dev-vs-diffbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crawl4ai-vs-diffbot.json",
        "title": "Crawl4AI vs Diffbot",
        "url": "https://www.anchorterminal.com/compare/crawl4ai-vs-diffbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crw-vs-diffbot.json",
        "title": "fastCRW vs Diffbot",
        "url": "https://www.anchorterminal.com/compare/crw-vs-diffbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/decodo-vs-diffbot.json",
        "title": "Decodo Web Data API vs Diffbot",
        "url": "https://www.anchorterminal.com/compare/decodo-vs-diffbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-jina-reader.json",
        "title": "Diffbot vs Jina Reader",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-jina-reader"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrape-do.json",
        "title": "Diffbot vs Scrape.do",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrape-do"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrapeless.json",
        "title": "Diffbot vs Scrapeless",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrapeless"
      },
      {
        "json": "https://www.anchorterminal.com/compare/browseract-vs-nexscope.json",
        "title": "BrowserAct vs Nexscope",
        "url": "https://www.anchorterminal.com/compare/browseract-vs-nexscope"
      },
      {
        "json": "https://www.anchorterminal.com/compare/context-dev-vs-nexscope.json",
        "title": "Context.dev vs Nexscope",
        "url": "https://www.anchorterminal.com/compare/context-dev-vs-nexscope"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crawl4ai-vs-nexscope.json",
        "title": "Crawl4AI vs Nexscope",
        "url": "https://www.anchorterminal.com/compare/crawl4ai-vs-nexscope"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crw-vs-nexscope.json",
        "title": "fastCRW vs Nexscope",
        "url": "https://www.anchorterminal.com/compare/crw-vs-nexscope"
      },
      {
        "json": "https://www.anchorterminal.com/compare/decodo-vs-nexscope.json",
        "title": "Decodo Web Data API vs Nexscope",
        "url": "https://www.anchorterminal.com/compare/decodo-vs-nexscope"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-firecrawl-mcp.json",
        "title": "Diffbot vs Firecrawl MCP",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-firecrawl-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-jevcrawl.json",
        "title": "Diffbot vs jevcrawl",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-jevcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-microlink.json",
        "title": "Diffbot vs Microlink",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-microlink"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-olostep.json",
        "title": "Diffbot vs Olostep",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-olostep"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-outcrawl.json",
        "title": "Diffbot vs Outcrawl",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-outcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-oxylabs-web-scraper.json",
        "title": "Diffbot vs Oxylabs Web Scraper API",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-oxylabs-web-scraper"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-printfriendly-mcp.json",
        "title": "Diffbot vs PrintFriendly MCP server",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-printfriendly-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-qovia.json",
        "title": "Diffbot vs Qovia",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-qovia"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrapeatlas.json",
        "title": "Diffbot vs ScrapeAtlas",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrapeatlas"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrapegraphai.json",
        "title": "Diffbot vs ScrapeGraphAI",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrapegraphai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrapeops.json",
        "title": "Diffbot vs ScrapeOps Proxy API Aggregator",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrapeops"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scraperapi.json",
        "title": "Diffbot vs ScraperAPI",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scraperapi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrapewise.json",
        "title": "Diffbot vs Scrapewise",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrapewise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrapfly.json",
        "title": "Diffbot vs Scrapfly",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrapfly"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrapingant.json",
        "title": "Diffbot vs ScrapingAnt",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrapingant"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrapingbee.json",
        "title": "Diffbot vs ScrapingBee",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrapingbee"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrapingdog.json",
        "title": "Diffbot vs Scrapingdog",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrapingdog"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-soldfetch.json",
        "title": "Diffbot vs SoldFetch",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-soldfetch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-spider-cloud.json",
        "title": "Diffbot vs Spider",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-spider-cloud"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-webscraping-ai.json",
        "title": "Diffbot vs WebScraping.AI",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-webscraping-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-zenrows.json",
        "title": "Diffbot vs ZenRows",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-zenrows"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-zyte.json",
        "title": "Diffbot vs Zyte API",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-zyte"
      },
      {
        "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-nexscope.json",
        "title": "Firecrawl MCP vs Nexscope",
        "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-nexscope"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jevcrawl-vs-nexscope.json",
        "title": "jevcrawl vs Nexscope",
        "url": "https://www.anchorterminal.com/compare/jevcrawl-vs-nexscope"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microlink-vs-nexscope.json",
        "title": "Microlink vs Nexscope",
        "url": "https://www.anchorterminal.com/compare/microlink-vs-nexscope"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-olostep.json",
        "title": "Nexscope vs Olostep",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-olostep"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-outcrawl.json",
        "title": "Nexscope vs Outcrawl",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-outcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-oxylabs-web-scraper.json",
        "title": "Nexscope vs Oxylabs Web Scraper API",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-oxylabs-web-scraper"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-printfriendly-mcp.json",
        "title": "Nexscope vs PrintFriendly MCP server",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-printfriendly-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-qovia.json",
        "title": "Nexscope vs Qovia",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-qovia"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-scrapeatlas.json",
        "title": "Nexscope vs ScrapeAtlas",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-scrapeatlas"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-scrapegraphai.json",
        "title": "Nexscope vs ScrapeGraphAI",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-scrapegraphai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-scrapeops.json",
        "title": "Nexscope vs ScrapeOps Proxy API Aggregator",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-scrapeops"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-scraperapi.json",
        "title": "Nexscope vs ScraperAPI",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-scraperapi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-scrapewise.json",
        "title": "Nexscope vs Scrapewise",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-scrapewise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-scrapfly.json",
        "title": "Nexscope vs Scrapfly",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-scrapfly"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingant.json",
        "title": "Nexscope vs ScrapingAnt",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingant"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingbee.json",
        "title": "Nexscope vs ScrapingBee",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingbee"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingdog.json",
        "title": "Nexscope vs Scrapingdog",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingdog"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-soldfetch.json",
        "title": "Nexscope vs SoldFetch",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-soldfetch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-spider-cloud.json",
        "title": "Nexscope vs Spider",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-spider-cloud"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-webscraping-ai.json",
        "title": "Nexscope vs WebScraping.AI",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-webscraping-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-zenrows.json",
        "title": "Nexscope vs ZenRows",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-zenrows"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-zyte.json",
        "title": "Nexscope vs Zyte API",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-zyte"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-diffbot.json",
        "title": "Apify MCP Server vs Diffbot",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-diffbot"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 16,
        "diffbot": 55,
        "edge": "diffbot",
        "key": "reliability",
        "name": "Reliability",
        "nexscope": 39,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 19,
        "diffbot": 83,
        "edge": "diffbot",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "nexscope": 64,
        "weight": 13
      },
      {
        "by": 19,
        "diffbot": 63,
        "edge": "diffbot",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "nexscope": 44,
        "weight": 13
      },
      {
        "by": 20,
        "diffbot": 21,
        "edge": "nexscope",
        "key": "security",
        "name": "Security \u0026 auth",
        "nexscope": 41,
        "weight": 14
      },
      {
        "by": 5,
        "diffbot": 40,
        "edge": "diffbot",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "nexscope": 35,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 12,
        "diffbot": 77,
        "edge": "diffbot",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "nexscope": 65,
        "weight": 7
      },
      {
        "by": 27,
        "diffbot": 68,
        "edge": "diffbot",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "nexscope": 41,
        "weight": 7
      }
    ],
    "summary": "Diffbot scores 56.1 (C) on agent readiness against Nexscope's 46.2 (D), and leads in 6 of 7 scored categories. Nexscope leads on security \u0026 auth. Both do extraction.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "diffbot": "Extract returns typed JSON for articles, products, discussions and other page types with no selectors to write, under a public OpenAPI 3.1 contract and a free plan that needs no card. The API token travels in the URL query string, tokens carry no scopes, and no security page, certification or security.txt was found.",
      "nexscope": "An agent can reach Amazon, TikTok Shop, Temu, 1688 and other marketplace data, plus image and video models, on one credit balance through a remote MCP server with OAuth or a REST API with a public OpenAPI file. The connection loads 382 tools at once, and there is no status page, changelog or idempotency key."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/diffbot-vs-nexscope",
    "json": "https://www.anchorterminal.com/compare/diffbot-vs-nexscope.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/diffbot-vs-nexscope.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/diffbot-vs-nexscope.min.md"
  },
  "markdown": "Diffbot scores 56.1 (C) on agent readiness against Nexscope's 46.2 (D), and leads in 6 of 7 scored categories. Nexscope leads on security \u0026 auth. Both do extraction.\n\n- Diffbot: grade C, 56.1/100, rank #854 of 1520. Markdown https://www.anchorterminal.com/tools/diffbot.md · JSON https://www.anchorterminal.com/api/v1/tools/diffbot.json\n- Nexscope: grade D, 46.2/100, rank #1191 of 1520. Markdown https://www.anchorterminal.com/tools/nexscope.md · JSON https://www.anchorterminal.com/api/v1/tools/nexscope.json\n- Best web scraping and crawling APIs for AI agents: https://www.anchorterminal.com/best/web-scrapers/index.md\n- All 533 scrapers comparisons: https://www.anchorterminal.com/compare/web-scrapers/index.md\n\n## Which one, for what\n\n### Diffbot (C)\n\nGood for: Agents that want typed article, product or discussion data from arbitrary pages without writing selectors, and teams that also want the Knowledge Graph.\n\nAhead on:\n- Reliability, 55 against 39\n- Schema \u0026 documentation, 83 against 64\n- Agent ergonomics, 63 against 44\n- Payments \u0026 pricing, 40 against 35\n- Maintenance \u0026 community, 77 against 65\n- Transparency \u0026 trust, 68 against 41\n\nWatch for: The token is sent as the `token` query parameter on Extract and Knowledge Graph calls. It is the only scheme in the OpenAPI file\n\n### Nexscope (D)\n\nGood for: Agents that research ecommerce products, competitors, keywords, sourcing and patents across Amazon, TikTok Shop, Walmart, Temu, 1688 and other marketplaces, and that also make listing images and video, on one credit balance.\n\nAhead on:\n- Security \u0026 auth, 41 against 21\n\nWatch for: The MCP connection advertises the full catalogue of 382 tools, with no toolsets or read-only subset\n\n\n## Why the edge\n\n### Transparency \u0026 trust: Diffbot +27\n\n- Diffbot (68): A closed service under undated Terms of Use that cover the Site and the Service, cap liability at $10 and grant Diffbot a perpetual licence to process submitted queries. The clients and skills are MIT (13 of 30). The privacy policy of 29 August 2025 says query history and API calls are stored against the API key and kept no longer than necessary, with no retention period given. The GDPR and data rights page was not read (14 of 30). There is no deprecation policy. The changelog carries dated notices, such as a May 2024 entry announcing a field removal for 30 August 2024, and the terms give 14 days' notice of fee changes (8 of 20). The privacy policy names its service providers one by one, among them AWS, Stripe, Intercom, Salesforce, Slack and Amplitude, and says all are in the United States (14 of 20). All per the 9 October check, not re-read on 4 November. 13 + 14 + 8 + 14 = 49.\n- Nexscope (41): The editorial half. The service is closed. The terms (8 October 2026) name ECOCREATE TECHNOLOGY PTE. LTD. under Singapore law with no registration number or address. The repository's MIT licence covers client code only, and the documentation and definitions stay copyright Nexscope. Scrapewise earned 15 for closed terms with MIT side code (15 of 30). The privacy policy (8 October 2026) says uploads are not used to train AI models and that connected selling-partner data is deleted or de-identified when no longer needed, but 'this policy does not specify a single deletion deadline for all data', and no DPA was found. SandBase took 12 with no retention periods (10 of 30). No deprecation policy or dated notices. The terms promise notice of material changes before they take effect where practicable, and the MCP map keeps a legacy v1 beside v2 (3 of 20). Analytics and advertising vendors are named (Google Analytics, Microsoft Clarity, Ahrefs, Google Ads, X, FirstPromoter), but hosting, AI processing and payment providers only by type, with no data locations. The repository's source notes say supplier references 'are presented as Nexscope', so the data suppliers go unnamed except LinkFox Agent for 1688 authorisation (5 of 20). 15+10+3+5 = 33. The provenance half is computed from the provenance block.\n\n### Security \u0026 auth: Nexscope +20\n\n- Diffbot (21): One token per account, sent in the URL query string as the documented and only scheme in the OpenAPI file. Tokens are revocable in the dashboard per a June 2025 changelog title, and child tokens exist on Plus and above (20 of 30, less 10 for the secret in the URL, so 10). Child tokens have the same rights as the primary one and there is no read-only mode. The skills limit the agent to the `db` binary through `allowed-tools` (5 of 20). The API returns untrusted web content and no guidance on prompt injection was found (0 of 15). The token details page shows usage activity and an Account API reports usage. No per-call log was found (6 of 15). No security.txt, security page, certification or bug bounty was found on the pages read, and the privacy policy says some API calls rely on HTTP without encryption (0 of 20). Site pages per the 9 October check, not re-read on 4 November. OSV lists no advisory for `diffbot` on PyPI or `@diffbot/typescript` on npm on 4 November. 10 + 5 + 0 + 6 + 0 = 21.\n- Nexscope (41): The MCP server takes OAuth 2.1 with PKCE and one scope, `mcp:tools`, per the tool pages, or a Bearer `nk-` API key. Keys are created by a person under API Access, shown once, and can be expired, disabled or deleted, with no scopes or rotation found. The OAuth metadata on api.nexscope.ai wasn't read. No query-string key option was found. Manifold earned 22 with OAuth and hashed keys whose storage it documents (20 of 30). Most tools read. Writes exist (1688 procurement on the user's own buyer account, Amazon Ads entity operations through an owned connection, paid generation jobs), and the 1688 calls need an explicit JSON `true` per action after a preview, with the guide saying to get the user's approval first. Credits cap spend. No read-only key or tool allowlist (12 of 20). Tools return third-party listings, reviews, social posts and web pages, and no prompt-injection guidance was found. Manifold, the closest marketing-data MCP, took 0 (0). The Account credits and Account usage APIs, `costToken` in data responses and credits charged on task results give per-call visibility. No key-level audit was found (9 of 15). security.txt answered a client error. No disclosure policy, bug bounty or certification found (0 of 20). 20+12+0+9+0 = 41.\n\n### Schema \u0026 documentation: Diffbot +19\n\n- Diffbot (83): The Extract APIs have a public OpenAPI 3.1.0 file, version 1.1.0, with 13 operations, and the reference pages are generated from it. We read that file and one rendered page. The descriptions for Crawl, Knowledge Graph and Web Search were not read (25). llms.txt exists but is a short index with no Markdown twins of the docs pages found (5 of 10). The Analyze API page has sections on when to use it and when not to (17 of 20). Parameters are typed, `url` is the one required field and the file has 15 enums, but `fields` is a comma-separated string and the file defines no shared response schemas (10 of 15). The file carries 24 examples. It documents only 200 and 500, with separate docs pages for 401, 404, 429 and 457 (11 of 15). The path is versioned `/v3` and a dated changelog with RSS runs from 2015 to 15 June 2026 (15). All per the 9 October check, not re-read on 4 November (terms bar automated access to the site). 25 + 5 + 17 + 10 + 11 + 15 = 83.\n- Nexscope (64): A public OpenAPI 3.1 file at api.nexscope.ai/openapi.json, about 3.8 MB, linked from the quickstart. Visible request bodies are typed with required fields, patterns, enums and `additionalProperties: false`, but responses are open `data` objects and the components section, with the security scheme and the shared error response, wasn't reached. In the repository 166 of 252 request definitions are field descriptors rather than JSON Schema. The hosted tools/list wasn't read. SoldFetch took 17 with untyped responses and SandBase 22 with components unread (19 of 25). llms.txt on www.nexscope.ai and Markdown references for every API in the repository (10). MCP tool descriptions are one line ('Find Amazon products by keyword and marketplace. Results come back as structured JSON.'), with no when-not-to-use. The repository's references carry long trigger text ('trigger this skill whenever their need involves real-time Amazon search results'), not guidance on when to pick another tool (10 of 20). Tool pages list types, defaults, enums and length limits, but the Amazon Search page marks no argument required and omits the `keyword` its own examples pass, and many limits sit in prose (8 of 15). Every API has a request sample, a response fixture and cURL, JavaScript and Python clients, though most fixtures are labelled historical. Errors are an HTTP table, two named codes (11209, 12001) and a semantic error response whose schema wasn't read. MCP errors aren't documented (10 of 15). Path versioning under /v1, MCP v2 beside a legacy v1, and a dated OpenAPI version label, but no public changelog. SandBase earned 7 on the same pattern (7 of 15). 19+10+10+8+10+7 = 64.\n\n### Agent ergonomics: Diffbot +19\n\n- Diffbot (63): Graded on the REST API, with the skills noted. `mode` limits extraction to one page type, `fields` adds optional fields and `discussion=false` drops comments, but an article response carries both `html` and `text` with no way found to drop either. The skills return Markdown by default (14 of 25). A single-URL call has no pagination. Web Search takes `size` and `maxTokens` and DQL takes `size` per the client. Crawl result paging was not read (10 of 20). Errors are JSON with `errorCode` and `error` and six docs pages. A failed extraction can arrive in a 200, and the 429 text says the site received too many requests when the cause is the caller's plan limit (12 of 20). Extract calls are GET reads and safe to retry. Whether a failed call uses a credit was not found, and there is no idempotency key for creating crawl jobs or custom APIs (12 of 20). Only `url` and `token` are required, with official Python and TypeScript clients and a CLI (15). Docs per the 9 October check, not re-read on 4 November. The Python client 3.1.0 (29 October 2026) adds a `snippet_length` option that maps to the Web Search API's `snippetLength`. 14 + 10 + 12 + 12 + 15 = 63.\n- Nexscope (44): Read on the MCP server, with the REST API where a line covers it. The MCP map lists 382 tools and says the category manifests 'narrow metadata for your integration; the MCP connection still advertises the full catalog'. That is more than 30 tools with no toolsets, dynamic loading or read-only subset found (5). Search tools page by `page` (about 20 results), with filters such as marketplace, category node, sort and device per tool, but no general pagination model or field selection, and output size depends on each tool (12 of 20). By default business errors answer HTTP 200 with an outer `code`. The `X-Nexscope-Http-Status: semantic` header maps them to HTTP statuses, the OpenAPI file names codes such as `DATA_IMAGE_DOWNLOAD_FAILED` and `CAPABILITY_BACKEND_UNAVAILABLE` in field text, and MCP errors aren't documented. SandBase earned 16 with typed bridge errors (11 of 20). Data calls only read. No idempotency keys and no readOnlyHint or destructiveHint documented. Async jobs return a `taskId` with a poll tool and a rule not to resubmit, and 1688 order, payment-link, receipt and cancel calls need an explicit JSON `true` confirmation (8 of 20). Few required parameters with defaults on most. No official SDK package, only standard-library clients in the repository for JavaScript and Python, which SoldFetch earned 8 for (8 of 15). 5+12+11+8+8 = 44.\n\n### Reliability: Diffbot +16\n\n- Diffbot (55): Graded as a hosted API. status.diffbot.com is a Pingdom public report with 13 checks, among them Analyze API, Article API, Crawlbot and Websearch, with daily uptime for seven days and no incident notes (15 of 20). No 90-day record can be read. In the week to 9 October 2026 Analyze API shows 99.69 per cent, with 2, 11 and 17 minutes down on 4, 5 and 6 October, and Article API 5, 9 and 2 minutes on 5 to 7 October (5 of 30, the line for no readable history). Rate limits are published per plan, 5 calls a minute on Free, 5 a second on Startup and 25 a second on Plus (15). The 429 page says to pause one second and back off. No `Retry-After` header is documented, though the official client reads one (10 of 15). No SLA was found (0). The Extract APIs are at `/v3` with no beta label (10). All per the 9 October check, not re-read on 4 November: Diffbot's terms bar software that scrapes or crawls the Site or Service, so its site and status report weren't fetched. 15 + 5 + 15 + 10 + 0 + 10 = 55.\n- Nexscope (39): Hosted lines, graded on the remote MCP server and the REST API at api.nexscope.ai. No status page is linked from the home page, llms.txt, the API quickstart or the MCP map, and none was found (0). With no page there is no incident history to read (5). The pricing page publishes requests a second and concurrency per plan, the same for API and MCP, with 1 and 1 on the trial, 3 and 2 on Starter, 5 and 4 on Growth, 10 and 8 on Pro (15). The quickstart calls 429 an 'execution admission rate limit' and says to honour `Retry-After` on 429 and 503 when present. No idempotency key exists. The repository says 'Do not blindly retry POST requests' and to check whether a task was created before resubmitting, and the MCP tool pages say a reconnecting client should query existing async work rather than resubmit. SoldFetch earned 15 with idempotency keys and SandBase 11 with keys on some writes, so guidance without keys earns 9 (9 of 15). No SLA, and the terms say 'We cannot guarantee the Service will be available at all times' (0). No beta or preview label on the API or the MCP server (10). 0+5+15+9+0+10 = 39.\n\n### Maintenance \u0026 community: Diffbot +12\n\n- Diffbot (77): Every dated source of the vendor's own was looked for in its GitHub repositories, since its site wasn't re-read. The official Python client, `diffbot` in the listing's packages, was tagged v3.1.0 on 29 October 2026, adding a Web Search `snippet_length` option, and the agent skills were tagged v1.2.0 the same day with rewritten skill content, 6 days before this check (30; was 10 on the API changelog's 15 June 2026 entry, which is per the 9 October check, not re-read on 4 November). In the 90 days from 6 August, the skills were tagged v1.1.0 (12 August, five new skills), v1.1.1 (13 August, a plugin marketplace manifest, counted half) and v1.2.0, and the Python client v3.0.0 (28 September) and v3.1.0, counted half as SDK tags, 3.5 in all (20). A public changelog with RSS and a support address exist. GitHub issues were not read (8 of 15 for a closed service). Python and TypeScript clients exist, but the docs named the packages `diffbot-python` and `diffbot-typescript` on 9 October while the repositories publish `diffbot` and `@diffbot/typescript`, and the TypeScript repository has no tag and no commit since 17 August 2026 (12 of 15). The Python repository tests on Python 3.9 to 3.13. We did not see CI results (7 of 10). 30 + 20 + 8 + 12 + 7 = 77.\n- Nexscope (65): Read as a closed service with a public documentation repository. The repository synced the released 1688 procurement contracts on 9 November 2026 and committed again on 10 November (30). No releases or changelog. The dated record is the registry's four versions on 14 and 16 October, repository commits on 8, 9, 20 and 29 October and 2, 9 and 10 November, and source notes dating WooCommerce (29 October) and design search (2 November) additions. SoldFetch earned 10 for dated commits without releases (10 of 20). No public changelog. Support is service@nexscope.ai, WhatsApp and a booked call, untested. The repository's one merged pull request came from the organisation itself, and GitHub's API refused us, so issues weren't read (5 of 15). The official MCP registry lists `io.github.nexscope/ecommerce`, active, latest 1.0.3 of 16 October 2026, read first-hand (15). A CI workflow runs offline catalogue validation and unit tests on standard-library clients with no dependencies. The run results weren't read (5 of 10). 30+10+5+15+5 = 65.\n\n## Score by category\n\n| Category | Weight | Diffbot | Nexscope | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 55 | 39 | Diffbot +16 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 83 | 64 | Diffbot +19 |\n| Agent ergonomics | 13% (16.2 this run) | 63 | 44 | Diffbot +19 |\n| Security \u0026 auth | 14% (17.5 this run) | 21 | 41 | Nexscope +20 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 35 | Diffbot +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 77 | 65 | Diffbot +12 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 68 | 41 | Diffbot +27 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **56.1 · C** | **46.2 · D** | |\n\n## Facts side by side\n\n| Fact | Diffbot | Nexscope |\n| --- | --- | --- |\n| Kind | HTTP API | Platform |\n| Vendor | Diffbot Technologies Corp. | ECOCREATE TECHNOLOGY PTE. LTD. |\n| Hosted endpoint | `https://api.diffbot.com/v3` | `https://api.nexscope.ai/mcp` |\n| Transports | HTTP | Streamable HTTP, HTTP |\n| Auth | API key | OAuth or key |\n| Pricing | Freemium | Paid |\n| Price for extraction | $0.90 per 1,000 pages | not published |\n| x402 | no | no |\n| Licence | Proprietary service under Diffbot's Terms of Use. The Python client, the TypeScript client and the agent skills are MIT | Proprietary hosted service under the Nexscope terms (last updated 8 October 2026), whose contracting party is ECOCREATE TECHNOLOGY PTE. LTD. of Singapore. The OpenAPI file's licence is 'Proprietary API; use subject to Nexscope Terms'. In github.com/nexscope-ai/nexscope-ecommerce-api only the example clients, validation scripts, tests and workflow are MIT. The API documentation, catalogue, definitions and sample data stay copyright Nexscope |\n| Tools exposed | none | 382 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `io.github.nexscope/ecommerce` |\n| Last release | 2026-10-29 | 2026-11-09 |\n| Terms last updated | no date given | not read yet |\n| Privacy policy last updated | 2025-08-29 | not read yet |\n| Customer content may train models | not found in the text | not read yet |\n| Terms restrict automated access | yes | not read yet |\n| Terms restrict benchmarking | not found in the text | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | yes | not read yet |\n| Popularity | 9 npm/wk | none |\n\n## How the scores have moved\n\n### Diffbot\n\n- +1.8 on 4 November 2026: product\n\n### Nexscope\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Diffbot.** Extract returns typed JSON for articles, products, discussions and other page types with no selectors to write, under a public OpenAPI 3.1 contract and a free plan that needs no card. The API token travels in the URL query string, tokens carry no scopes, and no security page, certification or security.txt was found.\n\n**Nexscope.** An agent can reach Amazon, TikTok Shop, Temu, 1688 and other marketplace data, plus image and video models, on one credit balance through a remote MCP server with OAuth or a REST API with a public OpenAPI file. The connection loads 382 tools at once, and there is no status page, changelog or idempotency key.\n\n## Before you call either\n\n### Diffbot\n\n1. Call `GET https://api.diffbot.com/v3/analyze?url=\u003cencoded URL\u003e\u0026token=\u003ctoken\u003e` when the page type is unknown. Use `/v3/article` or `/v3/product` to force one schema\n2. Keep the token out of logs and shared URLs. It sits in the query string, so any proxy or log that records the request URL records the token\n3. Stay under 5 calls a minute on Free, 5 a second on Startup and 25 a second on Plus. On 429 wait at least one second and back off\n4. Check a 200 response for `errorCode`. The official client raises `ExtractionError` when a 200 reports a failed extraction\n5. Set `useProxy=default` only when a site blocks the fetch. A proxied page costs 2 credits against 1\n6. Install `diffbot` from PyPI, not `diffbot-python`, which stopped at 0.3.0\n\n### Nexscope\n\n1. Check the outer `code` is 0 before reading `data`, or send `X-Nexscope-Http-Status: semantic` to get HTTP error statuses.\n2. Call an image or video tool once, keep the `taskId`, and poll `nexscope_media_task_result`. A second call bills a second job.\n3. Read the tool's credit cost before a call. Each tool costs at least 10 credits and some cost over 300.\n4. Before you set a 1688 confirmation field to `true`, show the user the preview and get approval.\n5. If the server returns 429 or 503, wait for `Retry-After` when present and back off.\n\n## Questions\n\n### Which is better for AI agents, Diffbot or Nexscope?\n\nDiffbot scores 56.1 (C) on agent readiness against Nexscope's 46.2 (D), and leads in 6 of 7 scored categories. Nexscope leads on security \u0026 auth.\n\n### Can an agent call Diffbot and Nexscope without installing anything?\n\nYes. Diffbot has a hosted endpoint at https://api.diffbot.com/v3 and Nexscope at https://api.nexscope.ai/mcp.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/diffbot-vs-nexscope.json, and with the fewest tokens: https://www.anchorterminal.com/compare/diffbot-vs-nexscope.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"diffbot\", \"b\": \"nexscope\"}`. From a terminal: `anchor compare diffbot nexscope`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/diffbot.json and https://www.anchorterminal.com/api/v1/tools/nexscope.json\n\n## Other comparisons with Diffbot or Nexscope\n\n- [Bright Data vs Diffbot](https://www.anchorterminal.com/compare/bright-data-vs-diffbot.md)\n- [BrowserAct vs Diffbot](https://www.anchorterminal.com/compare/browseract-vs-diffbot.md)\n- [Context.dev vs Diffbot](https://www.anchorterminal.com/compare/context-dev-vs-diffbot.md)\n- [Crawl4AI vs Diffbot](https://www.anchorterminal.com/compare/crawl4ai-vs-diffbot.md)\n- [fastCRW vs Diffbot](https://www.anchorterminal.com/compare/crw-vs-diffbot.md)\n- [Decodo Web Data API vs Diffbot](https://www.anchorterminal.com/compare/decodo-vs-diffbot.md)\n- [Diffbot vs Jina Reader](https://www.anchorterminal.com/compare/diffbot-vs-jina-reader.md)\n- [Diffbot vs Scrape.do](https://www.anchorterminal.com/compare/diffbot-vs-scrape-do.md)\n- [Diffbot vs Scrapeless](https://www.anchorterminal.com/compare/diffbot-vs-scrapeless.md)\n- [BrowserAct vs Nexscope](https://www.anchorterminal.com/compare/browseract-vs-nexscope.md)\n- [Context.dev vs Nexscope](https://www.anchorterminal.com/compare/context-dev-vs-nexscope.md)\n- [Crawl4AI vs Nexscope](https://www.anchorterminal.com/compare/crawl4ai-vs-nexscope.md)\n- [fastCRW vs Nexscope](https://www.anchorterminal.com/compare/crw-vs-nexscope.md)\n- [Decodo Web Data API vs Nexscope](https://www.anchorterminal.com/compare/decodo-vs-nexscope.md)\n- [Diffbot vs Firecrawl MCP](https://www.anchorterminal.com/compare/diffbot-vs-firecrawl-mcp.md)\n- [Diffbot vs jevcrawl](https://www.anchorterminal.com/compare/diffbot-vs-jevcrawl.md)\n- [Diffbot vs Microlink](https://www.anchorterminal.com/compare/diffbot-vs-microlink.md)\n- [Diffbot vs Olostep](https://www.anchorterminal.com/compare/diffbot-vs-olostep.md)\n- [Diffbot vs Outcrawl](https://www.anchorterminal.com/compare/diffbot-vs-outcrawl.md)\n- [Diffbot vs Oxylabs Web Scraper API](https://www.anchorterminal.com/compare/diffbot-vs-oxylabs-web-scraper.md)\n- [Diffbot vs PrintFriendly MCP server](https://www.anchorterminal.com/compare/diffbot-vs-printfriendly-mcp.md)\n- [Diffbot vs Qovia](https://www.anchorterminal.com/compare/diffbot-vs-qovia.md)\n- [Diffbot vs ScrapeAtlas](https://www.anchorterminal.com/compare/diffbot-vs-scrapeatlas.md)\n- [Diffbot vs ScrapeGraphAI](https://www.anchorterminal.com/compare/diffbot-vs-scrapegraphai.md)\n- [Diffbot vs ScrapeOps Proxy API Aggregator](https://www.anchorterminal.com/compare/diffbot-vs-scrapeops.md)\n- [Diffbot vs ScraperAPI](https://www.anchorterminal.com/compare/diffbot-vs-scraperapi.md)\n- [Diffbot vs Scrapewise](https://www.anchorterminal.com/compare/diffbot-vs-scrapewise.md)\n- [Diffbot vs Scrapfly](https://www.anchorterminal.com/compare/diffbot-vs-scrapfly.md)\n- [Diffbot vs ScrapingAnt](https://www.anchorterminal.com/compare/diffbot-vs-scrapingant.md)\n- [Diffbot vs ScrapingBee](https://www.anchorterminal.com/compare/diffbot-vs-scrapingbee.md)\n- [Diffbot vs Scrapingdog](https://www.anchorterminal.com/compare/diffbot-vs-scrapingdog.md)\n- [Diffbot vs SoldFetch](https://www.anchorterminal.com/compare/diffbot-vs-soldfetch.md)\n- [Diffbot vs Spider](https://www.anchorterminal.com/compare/diffbot-vs-spider-cloud.md)\n- [Diffbot vs WebScraping.AI](https://www.anchorterminal.com/compare/diffbot-vs-webscraping-ai.md)\n- [Diffbot vs ZenRows](https://www.anchorterminal.com/compare/diffbot-vs-zenrows.md)\n- [Diffbot vs Zyte API](https://www.anchorterminal.com/compare/diffbot-vs-zyte.md)\n- [Firecrawl MCP vs Nexscope](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-nexscope.md)\n- [jevcrawl vs Nexscope](https://www.anchorterminal.com/compare/jevcrawl-vs-nexscope.md)\n- [Microlink vs Nexscope](https://www.anchorterminal.com/compare/microlink-vs-nexscope.md)\n- [Nexscope vs Olostep](https://www.anchorterminal.com/compare/nexscope-vs-olostep.md)\n- [Nexscope vs Outcrawl](https://www.anchorterminal.com/compare/nexscope-vs-outcrawl.md)\n- [Nexscope vs Oxylabs Web Scraper API](https://www.anchorterminal.com/compare/nexscope-vs-oxylabs-web-scraper.md)\n- [Nexscope vs PrintFriendly MCP server](https://www.anchorterminal.com/compare/nexscope-vs-printfriendly-mcp.md)\n- [Nexscope vs Qovia](https://www.anchorterminal.com/compare/nexscope-vs-qovia.md)\n- [Nexscope vs ScrapeAtlas](https://www.anchorterminal.com/compare/nexscope-vs-scrapeatlas.md)\n- [Nexscope vs ScrapeGraphAI](https://www.anchorterminal.com/compare/nexscope-vs-scrapegraphai.md)\n- [Nexscope vs ScrapeOps Proxy API Aggregator](https://www.anchorterminal.com/compare/nexscope-vs-scrapeops.md)\n- [Nexscope vs ScraperAPI](https://www.anchorterminal.com/compare/nexscope-vs-scraperapi.md)\n- [Nexscope vs Scrapewise](https://www.anchorterminal.com/compare/nexscope-vs-scrapewise.md)\n- [Nexscope vs Scrapfly](https://www.anchorterminal.com/compare/nexscope-vs-scrapfly.md)\n- [Nexscope vs ScrapingAnt](https://www.anchorterminal.com/compare/nexscope-vs-scrapingant.md)\n- [Nexscope vs ScrapingBee](https://www.anchorterminal.com/compare/nexscope-vs-scrapingbee.md)\n- [Nexscope vs Scrapingdog](https://www.anchorterminal.com/compare/nexscope-vs-scrapingdog.md)\n- [Nexscope vs SoldFetch](https://www.anchorterminal.com/compare/nexscope-vs-soldfetch.md)\n- [Nexscope vs Spider](https://www.anchorterminal.com/compare/nexscope-vs-spider-cloud.md)\n- [Nexscope vs WebScraping.AI](https://www.anchorterminal.com/compare/nexscope-vs-webscraping-ai.md)\n- [Nexscope vs ZenRows](https://www.anchorterminal.com/compare/nexscope-vs-zenrows.md)\n- [Nexscope vs Zyte API](https://www.anchorterminal.com/compare/nexscope-vs-zyte.md)\n- [Apify MCP Server vs Diffbot](https://www.anchorterminal.com/compare/apify-mcp-vs-diffbot.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-11",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.7",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Diffbot vs Nexscope",
        "url": ""
      }
    ],
    "description": "Diffbot scores 56.1 (C) to Nexscope's 46.2 (D) for extraction. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Diffbot C 56.1",
      "Nexscope D 46.2",
      "scores"
    ],
    "h1": "Diffbot vs Nexscope",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/diffbot-vs-nexscope",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Diffbot vs Nexscope for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-11",
    "url": "https://www.anchorterminal.com/compare/diffbot-vs-nexscope"
  },
  "tokens": {
    "markdown": 7000,
    "slim": 1230
  },
  "version": 1
}