{ "data": { "a": { "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 } }, "answer": "Nexscope scores 46.2 (D) on agent readiness against Scrapingdog's 37.8 (F), and leads in 3 of 7 scored categories. Scrapingdog leads on reliability, agent ergonomics, payments \u0026 pricing and transparency \u0026 trust.", "b": { "slug": "scrapingdog", "name": "Scrapingdog", "vendor": "Scrapingdog (OpenData Labs)", "vendorUrl": "https://www.scrapingdog.com", "kind": "http-api", "category": "web-scrapers", "summary": "Web scraping API billed by credits.", "url": "https://www.anchorterminal.com/tools/scrapingdog", "markdownUrl": "https://www.anchorterminal.com/tools/scrapingdog.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/scrapingdog.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/scrapingdog.json", "dns": "scrapingdog.grade.anchorterminal.com", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://api.scrapingdog.com/scrape", "packages": [ { "registry": "npm", "name": "scrapingdog-mcp" }, { "registry": "npm", "name": "scrapingdog-sdk" }, { "registry": "pypi", "name": "scrapingdog" } ], "auth": "api-key", "authNotes": "The REST API takes the key in the api_key query parameter on every request, with no header option in the docs. The hosted MCP server at mcp.scrapingdog.com takes it as `Authorization: Bearer \u003ckey\u003e` and passes it on to the API. Team members have their own keys. A person signs up and copies the key from the dashboard; there is no programmatic key route (https://www.scrapingdog.com/agent-onboarding/SKILL.md).", "pricing": "freemium", "pricingNotes": "Free plan of 100 credits with 1 concurrent request, no card (the docs say 200 requests a month). Lite $40 a month (200,000 credits, 5 concurrent), Standard $90 (1M, 50), Pro $200 (3M, 100), Premium $350 (6M, 150), then plans up to $30,000 a month. Annual billing gives 2 months free. A plain request costs 1 credit, JS rendering 5, premium proxy or geotargeting 10, both 25, Google SERP 5 to 10, LinkedIn profiles 10 to 100. Failed requests aren't charged (https://www.scrapingdog.com/pricing/).", "priceSummary": "$40 / mo", "where": "both", "x402": { "level": "no", "evidence": "No x402 mention on the site, docs or pricing (checked 2026-09-30).", "endpoints": [] }, "toolCount": 35, "popularity": { "githubStars": 0, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://www.scrapingdog.com/documentation/", "llmsTxt": "https://www.scrapingdog.com/llms.txt", "registryName": "io.github.Darshan972/scrapingdog-mcp", "capabilities": [ "web.scrape", "web.extract", "web.search", "scraping.proxies", "scraping.js-render", "scraping.anti-bot", "scraping.screenshot", "scraping.serp" ], "tags": [ "hosted", "freemium", "no-card", "mcp", "llms-txt", "proxies", "closed-source", "python", "typescript" ], "lastRelease": "2026-07-31", "graded": true, "anchor": { "graded": true, "score": 37.8, "grade": "F", "agentReady": false, "rank": 1361, "ranked": true, "rankOf": 1520, "categoryRank": 33, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 52, "maintenance": 25, "payments": 40, "reliability": 49, "schema": 53, "security": 5, "transparency": 56 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-10" }, "negative": -2, "negativeNotes": [ "2026-08-01: the vendor-linked MCP server's web_scrape tool describes dynamic as `(API default: false)`, while https://www.scrapingdog.com/documentation/javascript-rendering/ says rendering is on by default at 5 credits. The MCP omits unset parameters, so a model that trusts the description pays 5 times the plain rate. Unchanged in the hosted server's code on 10 November 2026 (https://github.com/Darshan972/Scrapingdog-mcp, src/endpoints.ts and src/server.ts) (-2)." ], "verdict": "A plain request is 1 credit, about $0.20 per 1,000 on Lite, and failed requests aren't charged. The REST API takes its key only in the URL query string, and the MCP server describes JavaScript rendering as off by default when the API turns it on at 5 credits.", "bestFor": "A budget agent that wants parsed Google, Amazon or LinkedIn results and can keep the key out of logs.", "strengths": [ "A plain request is 1 credit, about $0.20 per 1,000 on Lite", "Parsed JSON endpoints for Google, Amazon, LinkedIn, YouTube and more under one key", "An agent onboarding guide gives every status code an action and says failed requests aren't charged", "Terms let you store and redistribute returned data during the subscription, and the privacy policy says API calls aren't stored or logged", "Concurrency per plan is published, from 1 up to 2,200" ], "weaknesses": [ "The REST API takes the key only in the URL query string", "Rendering defaults on at 5 credits, and the MCP's web_scrape description says the default is off", "The hosted MCP server is deployed from a personal account's repository with no tags, versions or changelog", "No changelog, security.txt or prompt-injection guidance, and the status page's monitors can't be read", "The free allowance differs between pricing (100 credits) and docs (200 a month)" ], "agentNotes": [ "Add dynamic=false unless the page needs JavaScript. It cuts the cost from 5 credits to 1, whatever the MCP description says", "Connect the hosted MCP with the key as a bearer header, and keep REST request URLs out of logs, since they carry api_key", "Set client timeouts above 60 seconds and retry 410 and 429 with backoff. Failures aren't billed", "Prefer the parsed endpoints (Google, Amazon) over scraping the raw page when one exists" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 37.8 } ], "editorialScores": { "ergonomics": 52, "maintenance": 25, "payments": 40, "reliability": 49, "schema": 53, "security": 5, "transparency": 37 }, "provenanceScore": 75, "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", "lastMoved": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl \"https://api.scrapingdog.com/scrape?api_key=$SCRAPINGDOG_API_KEY\u0026url=https://example.com\u0026dynamic=false\"", "claudeCode": "claude mcp add --transport http scrapingdog https://mcp.scrapingdog.com/mcp --header \"Authorization: Bearer $SCRAPINGDOG_API_KEY\"", "config": { "mcpServers": { "scrapingdog": { "headers": { "Authorization": "Bearer ${SCRAPINGDOG_API_KEY}" }, "url": "https://mcp.scrapingdog.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/web.scrape", "tool": "https://letme.dev/scrapingdog" }, "area": "web-data", "unitPrices": [ { "item": "Lite plan", "unit": "month", "usd": 40, "note": "200,000 credits, 5 concurrent" }, { "item": "Standard plan", "unit": "month", "usd": 90, "note": "1,000,000 credits, 50 concurrent" }, { "item": "Pro plan", "unit": "month", "usd": 200, "note": "3,000,000 credits, 100 concurrent" }, { "item": "Plain request on Lite", "unit": "1k-requests", "usd": 0.2, "note": "1 credit each, dynamic=false" }, { "item": "JS-rendered request on Lite", "unit": "1k-requests", "usd": 1, "note": "5 credits each, the default" } ], "provenance": { "legalEntity": "OpenData Labs Private Limited", "domain": "scrapingdog.com", "domainRegistered": "2020-04-04", "endpointOnVendorDomain": true, "terms": "https://www.scrapingdog.com/terms/", "privacy": "https://www.scrapingdog.com/privacy/", "statusPage": "https://stats.uptimerobot.com/SAQkQwbOYj", "changelog": "", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Legal entity from the site footer. The terms are governed by the laws of Rajasthan, India.", "The status page is a hosted UptimeRobot page linked from the footer." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/scrapingdog.json", "live": { "slug": "scrapingdog", "probe": { "target": "https://api.scrapingdog.com/scrape", "method": "get", "lastAt": "2026-11-11T06:59:59.819141232Z", "lastOk": true, "lastStatus": 400, "lastMs": 183, "authRequired": false, "uptime24h": 100, "uptime30d": 99.88, "p50ms24h": 143, "p95ms24h": 311, "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": 247 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 251 }, { "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": 250 }, { "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": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "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": 243 }, { "date": "2026-11-05", "probes": 185, "ok": 183 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 243, "ok": 243 }, { "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": "2026-10-08T00:00:00Z" }, "vendorStatus": { "page": "https://stats.uptimerobot.com/SAQkQwbOYj", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-11T05:35:46.244795147Z" }, "versions": [ { "registry": "mcp-registry", "name": "io.github.Darshan972/scrapingdog-mcp", "version": "0.1.1", "seenAt": "2026-11-10T19:22:02.357354042Z" }, { "registry": "npm", "name": "scrapingdog-mcp", "version": "0.1.1", "seenAt": "2026-11-11T06:34:26.232435146Z" }, { "registry": "npm", "name": "scrapingdog-sdk", "version": "1.0.1", "seenAt": "2026-11-11T06:34:27.086128808Z" }, { "registry": "pypi", "name": "scrapingdog", "version": "1.1.0", "released": "2026-07-31", "seenAt": "2026-11-11T06:34:28.50235172Z" } ], "npmWeekly": 61, "pypiWeekly": 11, "securityTxt": { "url": "https://scrapingdog.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-10T16:08:47.427721939Z" }, "llmsTxt": { "url": "https://www.scrapingdog.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-10T15:44:33.572026358Z" }, "domain": { "domain": "scrapingdog.com", "registered": "2020-04-04", "source": "https://rdap.verisign.com/com/v1/domain/scrapingdog.com", "checkedAt": "2026-11-08T14:58:15.757415363Z" }, "pages": [ { "url": "https://www.scrapingdog.com/terms/", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-10T16:45:51.663598484Z", "changedAt": "2026-11-04T08:44:58.963724214Z", "fingerprint": "ab8f40b925a9" }, { "url": "https://www.scrapingdog.com/pricing/", "kind": "pricing", "status": 304, "checkedAt": "2026-11-10T16:45:47.611823542Z", "changedAt": "2026-11-04T08:44:54.792406303Z", "fingerprint": "9cb54bf02af9" }, { "url": "https://www.scrapingdog.com/privacy/", "kind": "privacy", "status": 304, "checkedAt": "2026-11-10T16:45:49.648683579Z", "changedAt": "2026-11-04T08:44:57.071106175Z", "fingerprint": "eb900165657e" } ], "updatedAt": "2026-11-11T06:59:59.819141232Z" }, "streak": { "days": 34, "from": "2026-10-08", "sinceWatching": true, "best": 34 } }, "edges": [ { "by": 40, "category": "maintenance", "leads": "nexscope", "name": "Maintenance \u0026 community", "reasons": { "a": "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.", "b": "The newest dated releases are the SDKs and MCP server first published on 31 July and 1 August 2026, 102 days ago; no API changelog or later dated release found. The MCP repository became a hosted service at mcp.scrapingdog.com in commits of 25 and 26 October with no version bump, tag or changelog entry, so not a release (10 of 30). Nothing dated in the 90 days from 12 August (0 of 20). We couldn't read GitHub issues. The MCP repository has 13 commits, the last seven on 25 and 26 October, and support is by chat and email (5 of 25). Node and Python SDKs, current per the 1 October check; npm and PyPI weren't readable on 10 November (8 of 15). The MCP repository now runs typecheck, build and a smoke suite in CI before each deploy, with no tags or readable run results (2 of 10, the earlier partial held). Total 25." }, "scores": { "a": 65, "b": 25 } }, { "by": 36, "category": "security", "leads": "nexscope", "name": "Security \u0026 auth", "reasons": { "a": "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.", "b": "One account key with no scopes, and we found no rotation or revocation docs; team members get their own keys (10). The REST API takes the key only in the api_key query string, with no header option, so less 10 (0 of 30). The hosted MCP server takes the key as a bearer header, then passes it to the API in the query string. No read-only mode or least-privilege key. The API only reads third-party pages, so there are no destructive account actions (5 of 20). No prompt-injection guidance in the docs, the onboarding guide or the MCP README (0 of 15). No request log or per-call audit found; `/account` reports credits and concurrency only (0 of 15). No security.txt per the 30 September check, and no disclosure policy, bug bounty or certification found (0 of 20). Total 5." }, "scores": { "a": 41, "b": 5 } }, { "by": 15, "category": "transparency", "leads": "scrapingdog", "name": "Transparency \u0026 trust", "reasons": { "a": "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.", "b": "Closed service with terms revised 13 January 2026 (re-read 10 November), naming OpenData Labs Private Limited under the laws of Rajasthan, India, with no postal address. The MCP is MIT (15 of 30). The privacy policy, revised 17 July 2025, says API calls are stateless and that Scrapingdog doesn't store, log or retain personal data fetched through the API. A DPA is published. No retention periods for account data, per the 1 October check, not re-read on 10 November (22 of 30). No deprecation policy or dated notices found (0). No processors or data locations named (0 of 20). Total 37." }, "scores": { "a": 41, "b": 56 } }, { "by": 11, "category": "schema", "leads": "nexscope", "name": "Schema \u0026 documentation", "reasons": { "a": "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.", "b": "No OpenAPI spec found. The MCP builds typed zod inputs for 35 tools from a declarative registry, and ai_extract_rules is a JSON string (12 of 25). llms.txt at the site root, re-read on 10 November, links the docs and a Markdown onboarding guide for agents (10). MCP descriptions say what each endpoint does but not when to avoid it, and the web_scrape tool tells the model the API default for dynamic is false while the docs say rendering is on by default (10 of 20). Booleans, numbers and strings with few enums, plus the JSON-string field (9 of 15). Code examples on each docs page and 8 documented status codes (12 of 15). No changelog and no versioned API paths found (0). Total 53; the score published on 1 October was 43, ten below these lines, and is corrected to their sum." }, "scores": { "a": 64, "b": 53 } }, { "by": 10, "category": "reliability", "leads": "scrapingdog", "name": "Reliability", "reasons": { "a": "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.", "b": "The footer still links an UptimeRobot status page. Its monitors load only from UptimeRobot's /api/ path, which robots.txt disallows, and the page itself shows \"Loading...\" and a fetch error, so no component could be read (0 of 20). No readable incident history (5). Concurrency per plan is published, 1 on Free up to 2,200 on the top plan, and over the limit returns 429 (15). The agent onboarding guide linked from llms.txt says to retry 410, 429 and occasional 400s with backoff, not to retry 401 or 403, and that failed requests aren't charged; requests time out after 60 seconds. No Retry-After or idempotency keys (12 of 15). A public SLA page says Scrapingdog aims for 99 per cent monthly uptime and compensates downtime in credits, with no measurement method or date, per the 1 October check, not re-read on 10 November (7 of 10, the earlier partial held). Generally available (10). Total 49." }, "scores": { "a": 39, "b": 49 } }, { "by": 8, "category": "ergonomics", "leads": "scrapingdog", "name": "Agent ergonomics", "reasons": { "a": "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.", "b": "35 MCP tools with no toolsets or subsets (5 of 25). markdown=true, ai_query and parsed JSON endpoints for Google, Amazon and LinkedIn keep responses smaller. No documented pagination or size limits on the raw scrape (12 of 20). The docs list 8 status codes with meanings, and the agent onboarding guide gives each one an action (fix parameters on 400, check the key with /account on 401, a human upgrades on 403, lower concurrency and back off on 429, retry 410 once), with whether it's charged; the MCP passes the status and body back (20 of 20). Failed requests aren't billed, but no tool annotations or idempotency guidance (5 of 20). Only url is required, but rendering defaults on at 5 credits and the MCP describes it as off. Node and Python SDKs (10 of 15). Total 52." }, "scores": { "a": 44, "b": 52 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "ECOCREATE TECHNOLOGY PTE. LTD.", "b": "Scrapingdog (OpenData Labs)", "name": "Vendor" }, { "a": "https://api.nexscope.ai/mcp", "b": "https://api.scrapingdog.com/scrape", "name": "Hosted endpoint" }, { "a": "Streamable HTTP, HTTP", "b": "HTTP, Streamable HTTP, stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "API key", "name": "Auth" }, { "a": "Paid", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "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", "b": "none", "name": "Licence" }, { "a": "382", "b": "35", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "io.github.nexscope/ecommerce", "b": "io.github.Darshan972/scrapingdog-mcp", "name": "MCP registry" }, { "a": "2026-11-09", "b": "2026-07-31", "name": "Last release" }, { "a": "not read yet", "b": "2026-01-13", "name": "Terms last updated" }, { "a": "not read yet", "b": "2025-07-17", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "0 stars", "name": "Popularity" }, { "a": "none", "b": "3/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Nexscope scores 46.2 (D) on agent readiness against Scrapingdog's 37.8 (F), and leads in 3 of 7 scored categories. Scrapingdog leads on reliability, agent ergonomics, payments \u0026 pricing and transparency \u0026 trust.", "question": "Which is better for AI agents, Nexscope or Scrapingdog?" }, { "answer": "Yes. Nexscope has a hosted endpoint at https://api.nexscope.ai/mcp and Scrapingdog at https://api.scrapingdog.com/scrape.", "question": "Can an agent call Nexscope and Scrapingdog without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 64 against 53", "Security \u0026 auth, 41 against 5", "Maintenance \u0026 community, 65 against 25" ], "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" }, { "aheadOn": [ "Reliability, 49 against 39", "Agent ergonomics, 52 against 44", "Payments \u0026 pricing, 40 against 35", "Transparency \u0026 trust, 56 against 41" ], "also": [ "Runs on your own machine" ], "goodFor": "A budget agent that wants parsed Google, Amazon or LinkedIn results and can keep the key out of logs.", "slug": "scrapingdog", "watchFor": "The REST API takes the key only in the URL query string" } ], "history": { "nexscope": null, "scrapingdog": [ { "causes": [ "evidence", "correction", "time" ], "date": "2026-11-10", "delta": -1.5, "from": 39.3, "fromGrade": "E", "to": 37.8, "toGrade": "F" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 39.2, "fromGrade": "E", "to": 39.3, "toGrade": "E" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.1, "from": 39.3, "fromGrade": "E", "to": 39.2, "toGrade": "E" } ] }, "job": { "capability": "web.extract", "name": "Extraction" }, "others": [ { "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapingdog.json", "title": "Apify MCP Server vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapingdog.json", "title": "Bright Data vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/browseract-vs-scrapingdog.json", "title": "BrowserAct vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/browseract-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/context-dev-vs-scrapingdog.json", "title": "Context.dev vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/context-dev-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/crawl4ai-vs-scrapingdog.json", "title": "Crawl4AI vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/crawl4ai-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/crw-vs-scrapingdog.json", "title": "fastCRW vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/crw-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/decodo-vs-scrapingdog.json", "title": "Decodo Web Data API vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/decodo-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/jevcrawl-vs-scrapingdog.json", "title": "jevcrawl vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/jevcrawl-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/jina-reader-vs-scrapingdog.json", "title": "Jina Reader vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/jina-reader-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/microlink-vs-scrapingdog.json", "title": "Microlink vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/microlink-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/olostep-vs-scrapingdog.json", "title": "Olostep vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/olostep-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/outcrawl-vs-scrapingdog.json", "title": "Outcrawl vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/outcrawl-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/oxylabs-web-scraper-vs-scrapingdog.json", "title": "Oxylabs Web Scraper API vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/oxylabs-web-scraper-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scrape-do-vs-scrapingdog.json", "title": "Scrape.do vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/scrape-do-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scrapegraphai-vs-scrapingdog.json", "title": "ScrapeGraphAI vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/scrapegraphai-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scrapeless-vs-scrapingdog.json", "title": "Scrapeless vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/scrapeless-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scraperapi-vs-scrapingdog.json", "title": "ScraperAPI vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/scraperapi-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scrapewise-vs-scrapingdog.json", "title": "Scrapewise vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/scrapewise-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scrapfly-vs-scrapingdog.json", "title": "Scrapfly vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/scrapfly-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scrapingant-vs-scrapingdog.json", "title": "ScrapingAnt vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/scrapingant-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scrapingbee-vs-scrapingdog.json", "title": "ScrapingBee vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/scrapingbee-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scrapingdog-vs-spider-cloud.json", "title": "Scrapingdog vs Spider", "url": "https://www.anchorterminal.com/compare/scrapingdog-vs-spider-cloud" }, { "json": "https://www.anchorterminal.com/compare/scrapingdog-vs-webscraping-ai.json", "title": "Scrapingdog vs WebScraping.AI", "url": "https://www.anchorterminal.com/compare/scrapingdog-vs-webscraping-ai" }, { "json": "https://www.anchorterminal.com/compare/scrapingdog-vs-zenrows.json", "title": "Scrapingdog vs ZenRows", "url": "https://www.anchorterminal.com/compare/scrapingdog-vs-zenrows" }, { "json": "https://www.anchorterminal.com/compare/scrapingdog-vs-zyte.json", "title": "Scrapingdog vs Zyte API", "url": "https://www.anchorterminal.com/compare/scrapingdog-vs-zyte" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingdog.json", "title": "Firecrawl MCP vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingdog" }, { "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-nexscope.json", "title": "Diffbot vs Nexscope", "url": "https://www.anchorterminal.com/compare/diffbot-vs-nexscope" }, { "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/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-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/qovia-vs-scrapingdog.json", "title": "Qovia vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/qovia-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scrapeatlas-vs-scrapingdog.json", "title": "ScrapeAtlas vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/scrapeatlas-vs-scrapingdog" }, { "json": "https://www.anchorterminal.com/compare/scrapingdog-vs-soldfetch.json", "title": "Scrapingdog vs SoldFetch", "url": "https://www.anchorterminal.com/compare/scrapingdog-vs-soldfetch" }, { "json": "https://www.anchorterminal.com/compare/scrapeops-vs-scrapingdog.json", "title": "ScrapeOps Proxy API Aggregator vs Scrapingdog", "url": "https://www.anchorterminal.com/compare/scrapeops-vs-scrapingdog" } ], "panel": null, "scores": [ { "by": 10, "edge": "scrapingdog", "key": "reliability", "name": "Reliability", "nexscope": 39, "scrapingdog": 49, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 11, "edge": "nexscope", "key": "schema", "name": "Schema \u0026 documentation", "nexscope": 64, "scrapingdog": 53, "weight": 13 }, { "by": 8, "edge": "scrapingdog", "key": "ergonomics", "name": "Agent ergonomics", "nexscope": 44, "scrapingdog": 52, "weight": 13 }, { "by": 36, "edge": "nexscope", "key": "security", "name": "Security \u0026 auth", "nexscope": 41, "scrapingdog": 5, "weight": 14 }, { "by": 5, "edge": "scrapingdog", "key": "payments", "name": "Payments \u0026 pricing", "nexscope": 35, "scrapingdog": 40, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 40, "edge": "nexscope", "key": "maintenance", "name": "Maintenance \u0026 community", "nexscope": 65, "scrapingdog": 25, "weight": 7 }, { "by": 15, "edge": "scrapingdog", "key": "transparency", "name": "Transparency \u0026 trust", "nexscope": 41, "scrapingdog": 56, "weight": 7 } ], "summary": "Nexscope scores 46.2 (D) on agent readiness against Scrapingdog's 37.8 (F), and leads in 3 of 7 scored categories. Scrapingdog leads on reliability, agent ergonomics, payments \u0026 pricing and transparency \u0026 trust. Both do extraction.", "tasks": null, "tutorials": [], "verdicts": { "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.", "scrapingdog": "A plain request is 1 credit, about $0.20 per 1,000 on Lite, and failed requests aren't charged. The REST API takes its key only in the URL query string, and the MCP server describes JavaScript rendering as off by default when the API turns it on at 5 credits." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingdog", "json": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingdog.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingdog.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingdog.min.md" }, "markdown": "Nexscope scores 46.2 (D) on agent readiness against Scrapingdog's 37.8 (F), and leads in 3 of 7 scored categories. Scrapingdog leads on reliability, agent ergonomics, payments \u0026 pricing and transparency \u0026 trust. Both do extraction.\n\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- Scrapingdog: grade F, 37.8/100, rank #1361 of 1520. Markdown https://www.anchorterminal.com/tools/scrapingdog.md · JSON https://www.anchorterminal.com/api/v1/tools/scrapingdog.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### 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- Schema \u0026 documentation, 64 against 53\n- Security \u0026 auth, 41 against 5\n- Maintenance \u0026 community, 65 against 25\n\nWatch for: The MCP connection advertises the full catalogue of 382 tools, with no toolsets or read-only subset\n\n### Scrapingdog (F)\n\nGood for: A budget agent that wants parsed Google, Amazon or LinkedIn results and can keep the key out of logs.\n\nAhead on:\n- Reliability, 49 against 39\n- Agent ergonomics, 52 against 44\n- Payments \u0026 pricing, 40 against 35\n- Transparency \u0026 trust, 56 against 41\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: The REST API takes the key only in the URL query string\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Nexscope +40\n\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- Scrapingdog (25): The newest dated releases are the SDKs and MCP server first published on 31 July and 1 August 2026, 102 days ago; no API changelog or later dated release found. The MCP repository became a hosted service at mcp.scrapingdog.com in commits of 25 and 26 October with no version bump, tag or changelog entry, so not a release (10 of 30). Nothing dated in the 90 days from 12 August (0 of 20). We couldn't read GitHub issues. The MCP repository has 13 commits, the last seven on 25 and 26 October, and support is by chat and email (5 of 25). Node and Python SDKs, current per the 1 October check; npm and PyPI weren't readable on 10 November (8 of 15). The MCP repository now runs typecheck, build and a smoke suite in CI before each deploy, with no tags or readable run results (2 of 10, the earlier partial held). Total 25.\n\n### Security \u0026 auth: Nexscope +36\n\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- Scrapingdog (5): One account key with no scopes, and we found no rotation or revocation docs; team members get their own keys (10). The REST API takes the key only in the api_key query string, with no header option, so less 10 (0 of 30). The hosted MCP server takes the key as a bearer header, then passes it to the API in the query string. No read-only mode or least-privilege key. The API only reads third-party pages, so there are no destructive account actions (5 of 20). No prompt-injection guidance in the docs, the onboarding guide or the MCP README (0 of 15). No request log or per-call audit found; `/account` reports credits and concurrency only (0 of 15). No security.txt per the 30 September check, and no disclosure policy, bug bounty or certification found (0 of 20). Total 5.\n\n### Transparency \u0026 trust: Scrapingdog +15\n\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- Scrapingdog (56): Closed service with terms revised 13 January 2026 (re-read 10 November), naming OpenData Labs Private Limited under the laws of Rajasthan, India, with no postal address. The MCP is MIT (15 of 30). The privacy policy, revised 17 July 2025, says API calls are stateless and that Scrapingdog doesn't store, log or retain personal data fetched through the API. A DPA is published. No retention periods for account data, per the 1 October check, not re-read on 10 November (22 of 30). No deprecation policy or dated notices found (0). No processors or data locations named (0 of 20). Total 37.\n\n### Schema \u0026 documentation: Nexscope +11\n\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- Scrapingdog (53): No OpenAPI spec found. The MCP builds typed zod inputs for 35 tools from a declarative registry, and ai_extract_rules is a JSON string (12 of 25). llms.txt at the site root, re-read on 10 November, links the docs and a Markdown onboarding guide for agents (10). MCP descriptions say what each endpoint does but not when to avoid it, and the web_scrape tool tells the model the API default for dynamic is false while the docs say rendering is on by default (10 of 20). Booleans, numbers and strings with few enums, plus the JSON-string field (9 of 15). Code examples on each docs page and 8 documented status codes (12 of 15). No changelog and no versioned API paths found (0). Total 53; the score published on 1 October was 43, ten below these lines, and is corrected to their sum.\n\n### Reliability: Scrapingdog +10\n\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- Scrapingdog (49): The footer still links an UptimeRobot status page. Its monitors load only from UptimeRobot's /api/ path, which robots.txt disallows, and the page itself shows \"Loading...\" and a fetch error, so no component could be read (0 of 20). No readable incident history (5). Concurrency per plan is published, 1 on Free up to 2,200 on the top plan, and over the limit returns 429 (15). The agent onboarding guide linked from llms.txt says to retry 410, 429 and occasional 400s with backoff, not to retry 401 or 403, and that failed requests aren't charged; requests time out after 60 seconds. No Retry-After or idempotency keys (12 of 15). A public SLA page says Scrapingdog aims for 99 per cent monthly uptime and compensates downtime in credits, with no measurement method or date, per the 1 October check, not re-read on 10 November (7 of 10, the earlier partial held). Generally available (10). Total 49.\n\n### Agent ergonomics: Scrapingdog +8\n\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- Scrapingdog (52): 35 MCP tools with no toolsets or subsets (5 of 25). markdown=true, ai_query and parsed JSON endpoints for Google, Amazon and LinkedIn keep responses smaller. No documented pagination or size limits on the raw scrape (12 of 20). The docs list 8 status codes with meanings, and the agent onboarding guide gives each one an action (fix parameters on 400, check the key with /account on 401, a human upgrades on 403, lower concurrency and back off on 429, retry 410 once), with whether it's charged; the MCP passes the status and body back (20 of 20). Failed requests aren't billed, but no tool annotations or idempotency guidance (5 of 20). Only url is required, but rendering defaults on at 5 credits and the MCP describes it as off. Node and Python SDKs (10 of 15). Total 52.\n\n## Score by category\n\n| Category | Weight | Nexscope | Scrapingdog | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 39 | 49 | Scrapingdog +10 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 64 | 53 | Nexscope +11 |\n| Agent ergonomics | 13% (16.2 this run) | 44 | 52 | Scrapingdog +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 41 | 5 | Nexscope +36 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 35 | 40 | Scrapingdog +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 65 | 25 | Nexscope +40 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 41 | 56 | Scrapingdog +15 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **46.2 · D** | **37.8 · F** | |\n\n## Facts side by side\n\n| Fact | Nexscope | Scrapingdog |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | ECOCREATE TECHNOLOGY PTE. LTD. | Scrapingdog (OpenData Labs) |\n| Hosted endpoint | `https://api.nexscope.ai/mcp` | `https://api.scrapingdog.com/scrape` |\n| Transports | Streamable HTTP, HTTP | HTTP, Streamable HTTP, stdio |\n| Auth | OAuth or key | API key |\n| Pricing | Paid | Freemium |\n| x402 | no | no |\n| Licence | 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 | none |\n| Tools exposed | 382 | 35 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | `io.github.nexscope/ecommerce` | `io.github.Darshan972/scrapingdog-mcp` |\n| Last release | 2026-11-09 | 2026-07-31 |\n| Terms last updated | not read yet | 2026-01-13 |\n| Privacy policy last updated | not read yet | 2025-07-17 |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | yes |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Popularity | none | 0 stars |\n| Agent reviews | none | 3/5 (2) |\n\n## How the scores have moved\n\n### Nexscope\n\nNo score change since it was listed.\n\n### Scrapingdog\n\n- -1.5 on 10 November 2026 (E to F): new evidence, correction, time\n- +0.1 on 27 October 2026: checklist\n- -0.1 on 8 October 2026: checklist\n\n## Verdicts\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**Scrapingdog.** A plain request is 1 credit, about $0.20 per 1,000 on Lite, and failed requests aren't charged. The REST API takes its key only in the URL query string, and the MCP server describes JavaScript rendering as off by default when the API turns it on at 5 credits.\n\n## Before you call either\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### Scrapingdog\n\n1. Add dynamic=false unless the page needs JavaScript. It cuts the cost from 5 credits to 1, whatever the MCP description says\n2. Connect the hosted MCP with the key as a bearer header, and keep REST request URLs out of logs, since they carry api_key\n3. Set client timeouts above 60 seconds and retry 410 and 429 with backoff. Failures aren't billed\n4. Prefer the parsed endpoints (Google, Amazon) over scraping the raw page when one exists\n\n## Questions\n\n### Which is better for AI agents, Nexscope or Scrapingdog?\n\nNexscope scores 46.2 (D) on agent readiness against Scrapingdog's 37.8 (F), and leads in 3 of 7 scored categories. Scrapingdog leads on reliability, agent ergonomics, payments \u0026 pricing and transparency \u0026 trust.\n\n### Can an agent call Nexscope and Scrapingdog without installing anything?\n\nYes. Nexscope has a hosted endpoint at https://api.nexscope.ai/mcp and Scrapingdog at https://api.scrapingdog.com/scrape.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/nexscope-vs-scrapingdog.json, and with the fewest tokens: https://www.anchorterminal.com/compare/nexscope-vs-scrapingdog.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"nexscope\", \"b\": \"scrapingdog\"}`. From a terminal: `anchor compare nexscope scrapingdog`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/nexscope.json and https://www.anchorterminal.com/api/v1/tools/scrapingdog.json\n\n## Other comparisons with Nexscope or Scrapingdog\n\n- [Apify MCP Server vs Scrapingdog](https://www.anchorterminal.com/compare/apify-mcp-vs-scrapingdog.md)\n- [Bright Data vs Scrapingdog](https://www.anchorterminal.com/compare/bright-data-vs-scrapingdog.md)\n- [BrowserAct vs Scrapingdog](https://www.anchorterminal.com/compare/browseract-vs-scrapingdog.md)\n- [Context.dev vs Scrapingdog](https://www.anchorterminal.com/compare/context-dev-vs-scrapingdog.md)\n- [Crawl4AI vs Scrapingdog](https://www.anchorterminal.com/compare/crawl4ai-vs-scrapingdog.md)\n- [fastCRW vs Scrapingdog](https://www.anchorterminal.com/compare/crw-vs-scrapingdog.md)\n- [Decodo Web Data API vs Scrapingdog](https://www.anchorterminal.com/compare/decodo-vs-scrapingdog.md)\n- [jevcrawl vs Scrapingdog](https://www.anchorterminal.com/compare/jevcrawl-vs-scrapingdog.md)\n- [Jina Reader vs Scrapingdog](https://www.anchorterminal.com/compare/jina-reader-vs-scrapingdog.md)\n- [Microlink vs Scrapingdog](https://www.anchorterminal.com/compare/microlink-vs-scrapingdog.md)\n- [Olostep vs Scrapingdog](https://www.anchorterminal.com/compare/olostep-vs-scrapingdog.md)\n- [Outcrawl vs Scrapingdog](https://www.anchorterminal.com/compare/outcrawl-vs-scrapingdog.md)\n- [Oxylabs Web Scraper API vs Scrapingdog](https://www.anchorterminal.com/compare/oxylabs-web-scraper-vs-scrapingdog.md)\n- [Scrape.do vs Scrapingdog](https://www.anchorterminal.com/compare/scrape-do-vs-scrapingdog.md)\n- [ScrapeGraphAI vs Scrapingdog](https://www.anchorterminal.com/compare/scrapegraphai-vs-scrapingdog.md)\n- [Scrapeless vs Scrapingdog](https://www.anchorterminal.com/compare/scrapeless-vs-scrapingdog.md)\n- [ScraperAPI vs Scrapingdog](https://www.anchorterminal.com/compare/scraperapi-vs-scrapingdog.md)\n- [Scrapewise vs Scrapingdog](https://www.anchorterminal.com/compare/scrapewise-vs-scrapingdog.md)\n- [Scrapfly vs Scrapingdog](https://www.anchorterminal.com/compare/scrapfly-vs-scrapingdog.md)\n- [ScrapingAnt vs Scrapingdog](https://www.anchorterminal.com/compare/scrapingant-vs-scrapingdog.md)\n- [ScrapingBee vs Scrapingdog](https://www.anchorterminal.com/compare/scrapingbee-vs-scrapingdog.md)\n- [Scrapingdog vs Spider](https://www.anchorterminal.com/compare/scrapingdog-vs-spider-cloud.md)\n- [Scrapingdog vs WebScraping.AI](https://www.anchorterminal.com/compare/scrapingdog-vs-webscraping-ai.md)\n- [Scrapingdog vs ZenRows](https://www.anchorterminal.com/compare/scrapingdog-vs-zenrows.md)\n- [Scrapingdog vs Zyte API](https://www.anchorterminal.com/compare/scrapingdog-vs-zyte.md)\n- [Firecrawl MCP vs Scrapingdog](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapingdog.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 Nexscope](https://www.anchorterminal.com/compare/diffbot-vs-nexscope.md)\n- [Diffbot vs Scrapingdog](https://www.anchorterminal.com/compare/diffbot-vs-scrapingdog.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 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- [Qovia vs Scrapingdog](https://www.anchorterminal.com/compare/qovia-vs-scrapingdog.md)\n- [ScrapeAtlas vs Scrapingdog](https://www.anchorterminal.com/compare/scrapeatlas-vs-scrapingdog.md)\n- [Scrapingdog vs SoldFetch](https://www.anchorterminal.com/compare/scrapingdog-vs-soldfetch.md)\n- [ScrapeOps Proxy API Aggregator vs Scrapingdog](https://www.anchorterminal.com/compare/scrapeops-vs-scrapingdog.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": "Nexscope vs Scrapingdog", "url": "" } ], "description": "Nexscope scores 46.2 (D) to Scrapingdog's 37.8 (F) for extraction. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Nexscope D 46.2", "Scrapingdog F 37.8", "scores" ], "h1": "Nexscope vs Scrapingdog", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/nexscope-vs-scrapingdog", "published": "2026-10-01", "section": "tools", "title": "Nexscope vs Scrapingdog for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-11", "url": "https://www.anchorterminal.com/compare/nexscope-vs-scrapingdog" }, "tokens": { "markdown": 6600, "slim": 1230 }, "version": 1 }