{
  "data": {
    "a": {
      "slug": "apify-mcp",
      "name": "Apify MCP Server",
      "vendor": "Apify",
      "vendorUrl": "https://apify.com",
      "company": "apify.com",
      "kind": "mcp",
      "category": "web-scrapers",
      "summary": "Exposes thousands of Apify Store Actors (scrapers, crawlers, automations) as dynamically discovered MCP tools, hosted at mcp.apify.com or run locally; supports OAuth, API tokens and agentic payments (x402 prepaid tokens, Skyfire).",
      "url": "https://www.anchorterminal.com/tools/apify-mcp",
      "markdownUrl": "https://www.anchorterminal.com/tools/apify-mcp.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/apify-mcp.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/apify-mcp.json",
      "dns": "apify-mcp.grade.anchorterminal.com",
      "repo": "https://github.com/apify/apify-mcp-server",
      "license": "MIT",
      "transports": [
        "stdio",
        "streamable-http"
      ],
      "remoteUrl": "https://mcp.apify.com",
      "packages": [
        {
          "registry": "npm",
          "name": "@apify/actors-mcp-server"
        }
      ],
      "auth": "mixed",
      "authNotes": "OAuth on mcp.apify.com, or an Apify API token as `Authorization: Bearer`. Tokens can be scoped to account or per-resource permissions, given an expiry date and rotated with a 24-hour overlap. The Apify API also accepts the token as a `token` query parameter. Without an account, an agent can buy an AGI prepaid token over x402 or MPP and use it as a Bearer token, or pay per request with Skyfire PAY tokens (Pay Per Event Actors only). `?tools=` selects categories or single tools.",
      "pricing": "freemium",
      "pricingNotes": "MCP server itself is free; Actor runs are billed on Apify plans: Free $0 with $5/month usage credit ($0.20 per compute unit), Starter $19/mo, Scale $199/mo ($0.16/CU), Business $999/mo ($0.13/CU), 10% off annual (https://apify.com/pricing).",
      "priceSummary": "$1 / call",
      "where": "both",
      "x402": {
        "level": "yes",
        "evidence": "AGI (agi.apify.com) sells a prepaid, spend-capped Apify token over x402 (exact scheme on Base or Solana) or MPP (charge on Tempo with USDC or pathUSD, or Solana with USDC or USDT), minimum $1, valid for 14 days with unused balance not refunded, usable as `Authorization: Bearer` against mcp.apify.com and api.apify.com for any Actor that uses limited permissions. AGI also runs single Actors for x402 `batch-settlement` on Base (`/api-proxy/actors/{actorId}/runs`, $1 minimum ceiling, real cost billed, unused channel balance refunded after 24 hours idle). The server's direct `?payment=x402` mode is still in its source, but the README dropped its documentation on 28 October 2026 (https://agi.apify.com/AGENTS.md; https://docs.apify.com/agents/payments.md; https://docs.apify.com/mcp.md, checked 2026-11-01).",
        "endpoints": [
          {
            "url": "https://agi.apify.com/protocols/x402/prepaid-tokens?amount=1\u0026currency=usd",
            "priceUsd": 1,
            "network": "eip155:8453"
          },
          {
            "url": "https://agi.apify.com/api-proxy/actors/{actorId}/runs?amount=1\u0026currency=usd",
            "priceUsd": 1,
            "network": "eip155:8453"
          }
        ]
      },
      "toolCount": 47,
      "popularity": {
        "githubStars": 8600,
        "npmWeekly": 15257,
        "pypiWeekly": null,
        "asOf": "2026-09-26"
      },
      "docsUrl": "https://github.com/apify/apify-mcp-server#readme",
      "registryName": "com.apify/apify-mcp-server",
      "capabilities": [
        "scraping.actors",
        "web.crawl"
      ],
      "tags": [
        "official",
        "hosted",
        "local",
        "open-source",
        "x402",
        "aggregator"
      ],
      "lastRelease": "2026-10-29",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 79,
        "grade": "A",
        "agentReady": true,
        "rank": 41,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 1,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 92,
          "maintenance": 95,
          "payments": 99,
          "reliability": 75,
          "schema": 92,
          "security": 62,
          "transparency": 86
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-01"
        },
        "negative": -5,
        "negativeNotes": [
          "-3: v0.16.0 on 2026-09-17 renamed get-actor-log to get-actor-run-log with no deprecation period, and the old name is now ignored without an error. It was flagged as breaking in the changelog on release day, so the lowest deduction (https://github.com/apify/apify-mcp-server/blob/master/CHANGELOG.md).",
          "-2: GHSA-6gr2-qh89-hxwm (CVE-2026-50143, CVSS 8.1, High). Versions before 0.10.11 built an Actor's MCP URL by joining strings, so a malicious Actor's webServerMcpPath could send the user's Apify token to another host. Fixed in 0.10.11 on 28 May 2026 and published as a GitHub advisory, about four months old, so 2 points rather than the full deduction for an exfiltration path. The Moderate GHSA-jwp7-wg77-3w9v (CVE-2026-46341), a fetch-apify-docs allowlist bypass fixed in 0.9.21 on 4 May 2026, wasn't deducted (https://github.com/apify/apify-mcp-server/security/advisories/GHSA-6gr2-qh89-hxwm; https://github.com/apify/apify-mcp-server/security/advisories/GHSA-jwp7-wg77-3w9v)."
        ],
        "verdict": "x402 on Apify's own domains, a prepaid token from agi.apify.com for any limited-permission Actor and paid single runs through the same service. Tool names and defaults still change between 0.x releases, with breaking changes flagged only on release day.",
        "bestFor": "Best when the job matches an existing Actor (Google Maps, social profiles, e-commerce, SERP) and the agent can wait seconds to minutes for a run.",
        "strengths": [
          "x402 on Apify's own domains, a prepaid token from agi.apify.com for any limited-permission Actor and x402 single runs billed at real cost",
          "14 tools by default out of 47, `?tools=` to pick categories, and readOnly, destructive and idempotent hints on every tool",
          "Scoped API tokens with expiry and a 24-hour rotation overlap, plus OAuth on the hosted server",
          "28 releases between 3 August and 29 October 2026, with breaking changes flagged in the changelog",
          "Free plan with $5 of monthly usage and no card"
        ],
        "weaknesses": [
          "0.19.0 and 0.20.0 (19 and 29 October 2026) changed tool behaviour with breaking changes flagged only on release day",
          "No prompt-injection guidance for scraped content, third-party Actor READMEs or remote Actor MCP results",
          "Telemetry and Sentry on by default, and Store searches send a model-written use case",
          "Prepaid tokens can't run Actors that need full permissions, and Skyfire covers Pay Per Event Actors only",
          "No SLA published for any self-serve plan"
        ],
        "agentNotes": [
          "Call fetch-actor-details before call-actor to get the input schema and the price",
          "Use call-actor-mcp-tool, not call-actor with `actor:tool`, for an Actor that runs an MCP server. List its tools first with fetch-actor-mcp-tool-list",
          "Read results with get-dataset-items and set `fields` and `limit`. The default is 20 rows",
          "Buy an AGI token to pay without an account. Tokens last 14 days, unused balance isn't refunded, and Actors needing full permissions refuse them",
          "Pin `?tools=` in production. The default tool set changes between versions"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 8,
        "avgRating": 3.4,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "A",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 79
          }
        ],
        "editorialScores": {
          "ergonomics": 92,
          "maintenance": 95,
          "payments": 99,
          "reliability": 75,
          "schema": 92,
          "security": 62,
          "transparency": 75
        },
        "provenanceScore": 97,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-01",
            "maintenance": "2026-11-01",
            "payments": "2026-11-01",
            "reliability": "2026-11-01",
            "schema": "2026-11-01",
            "security": "2026-11-01",
            "transparency": "2026-11-01"
          },
          "last": "2026-11-01",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-01",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "claudeCode": "claude mcp add --transport http apify https://mcp.apify.com --header \"Authorization: Bearer ${APIFY_TOKEN}\"",
        "config": {
          "mcpServers": {
            "apify": {
              "headers": {
                "Authorization": "Bearer ${APIFY_TOKEN}"
              },
              "url": "https://mcp.apify.com"
            }
          }
        },
        "x402": "curl -s -i -X POST 'https://agi.apify.com/protocols/x402/prepaid-tokens?amount=1\u0026currency=usd'\n# 402 -\u003e pay with PAYMENT-SIGNATURE (USDC, eip155:8453) -\u003e token in response\n# then: Authorization: Bearer \u003cprepaid token\u003e against https://mcp.apify.com"
      },
      "letme": {
        "capability": "https://letme.dev/scraping.actors",
        "tool": "https://letme.dev/apify-mcp"
      },
      "area": "web-data",
      "unitPrices": [
        {
          "item": "Compute unit, pay as you go",
          "unit": "compute-unit",
          "usd": 0.2
        }
      ],
      "provenance": {
        "legalEntity": "Apify Technologies s.r.o.",
        "domain": "apify.com",
        "domainRegistered": "2009-06-02",
        "endpointOnVendorDomain": true,
        "terms": "https://docs.apify.com/legal/general-terms-and-conditions",
        "privacy": "https://docs.apify.com/legal/privacy-policy",
        "statusPage": "https://status.apify.com",
        "changelog": "https://github.com/apify/apify-mcp-server/releases",
        "securityTxt": "valid",
        "checked": "2026-11-01",
        "score": 97
      },
      "requirements": {
        "setupChecked": true,
        "complianceChecked": true,
        "agentAlone": true,
        "card": "no",
        "freeTier": true,
        "minutes": 3,
        "credential": "mixed",
        "hosting": [
          "US"
        ],
        "euResidency": "unknown",
        "trainsOnData": "unknown",
        "zeroRetention": "unknown",
        "certifications": [
          "SOC 2 Type II",
          "GDPR"
        ],
        "dpa": true,
        "selfHost": "no"
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/apify-mcp.json",
      "live": {
        "slug": "apify-mcp",
        "probe": {
          "target": "https://mcp.apify.com",
          "method": "mcp-initialize",
          "lastAt": "2026-11-18T22:43:03.299737014Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 631,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 99.9,
          "p50ms24h": 274,
          "p95ms24h": 449,
          "samples24h": 241,
          "samples30d": 7837,
          "days": [
            {
              "date": "2026-10-18",
              "probes": 256,
              "ok": 256
            },
            {
              "date": "2026-10-19",
              "probes": 255,
              "ok": 255
            },
            {
              "date": "2026-10-20",
              "probes": 252,
              "ok": 251
            },
            {
              "date": "2026-10-21",
              "probes": 253,
              "ok": 252
            },
            {
              "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": 249
            },
            {
              "date": "2026-10-26",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-27",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-28",
              "probes": 251,
              "ok": 250
            },
            {
              "date": "2026-10-29",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-30",
              "probes": 248,
              "ok": 248
            },
            {
              "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": 243
            },
            {
              "date": "2026-11-08",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-09",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-10",
              "probes": 244,
              "ok": 243
            },
            {
              "date": "2026-11-11",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-12",
              "probes": 245,
              "ok": 244
            },
            {
              "date": "2026-11-13",
              "probes": 238,
              "ok": 237
            },
            {
              "date": "2026-11-14",
              "probes": 244,
              "ok": 243
            },
            {
              "date": "2026-11-15",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-16",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-17",
              "probes": 242,
              "ok": 242
            },
            {
              "date": "2026-11-18",
              "probes": 228,
              "ok": 228
            }
          ],
          "since": "2026-10-08T00:00:00Z"
        },
        "vendorStatus": {
          "page": "https://status.apify.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-11-18T22:37:07.239255054Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "apify/actors-mcp-server",
            "version": "v0.17.1",
            "released": "2026-09-30",
            "seenAt": "2026-10-01T13:17:39.020905395Z"
          },
          {
            "registry": "github",
            "name": "apify/apify-mcp-server",
            "version": "v0.21.12",
            "released": "2026-11-17",
            "seenAt": "2026-11-18T17:28:07.418458493Z"
          },
          {
            "registry": "mcp-registry",
            "name": "com.apify/apify-mcp-server",
            "version": "0.21.12",
            "seenAt": "2026-11-18T22:45:57.054523297Z"
          },
          {
            "registry": "npm",
            "name": "@apify/actors-mcp-server",
            "version": "0.21.12",
            "seenAt": "2026-11-18T17:28:06.490646008Z"
          }
        ],
        "githubStars": 16863,
        "npmWeekly": 51838,
        "securityTxt": {
          "url": "https://apify.com/.well-known/security.txt",
          "state": "valid",
          "expires": "2035-01-01T00:00:00.000Z",
          "checkedAt": "2026-11-18T16:30:41.036333906Z"
        },
        "domain": {
          "domain": "apify.com",
          "registered": "2009-06-02",
          "source": "https://rdap.verisign.com/com/v1/domain/apify.com",
          "checkedAt": "2026-11-15T15:28:15.986249241Z"
        },
        "pages": [
          {
            "url": "https://raw.githubusercontent.com/apify/apify-mcp-server/master/CHANGELOG.md",
            "kind": "deprecations",
            "status": 304,
            "checkedAt": "2026-11-18T21:54:16.857331946Z",
            "changedAt": "2026-11-17T21:13:34.002952489Z",
            "fingerprint": "085c97e69e5a"
          },
          {
            "url": "https://apify.com/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-11-18T21:33:05.033687696Z",
            "changedAt": "2026-11-18T21:33:05.033687696Z",
            "fingerprint": "c5f8cad9f944"
          },
          {
            "url": "https://docs.apify.com/legal/privacy-policy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-18T21:39:00.039713257Z",
            "changedAt": "2026-10-26T03:13:37.745025484Z",
            "fingerprint": "baa7a19d779b"
          },
          {
            "url": "https://docs.apify.com/legal/general-terms-and-conditions",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-11-18T21:38:57.784985065Z",
            "changedAt": "2026-10-22T01:14:33.334764567Z",
            "fingerprint": "48db3585a5d3"
          }
        ],
        "mcpTools": {
          "url": "https://mcp.apify.com",
          "checkedAt": "2026-11-18T04:21:42.529459414Z",
          "status": "auth",
          "note": "asks for credentials before listing its tools",
          "changedAt": "2026-09-28T21:55:37.935476956Z"
        },
        "github": {
          "repo": "apify/apify-mcp-server",
          "checkedAt": "2026-11-16T11:43:22.077552292Z",
          "stars": 16471,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-16T11:26:15Z",
          "openIssues": 225,
          "openPRs": 37,
          "issuesOpened90d": 303,
          "issuesClosed90d": 198,
          "prsMerged90d": 251,
          "ci": {
            "branch": "master",
            "runs": 50,
            "success": 37,
            "failure": 2,
            "other": 11,
            "latest": "success",
            "latestAt": "2026-11-16T11:05:53Z"
          },
          "advisories": [
            {
              "ghsa": "GHSA-957f-6f36-mv2h",
              "severity": "low",
              "published": "2026-11-12T18:59:22Z"
            },
            {
              "ghsa": "GHSA-ffrr-cj64-hrf5",
              "severity": "low",
              "published": "2026-11-09T12:40:27Z"
            },
            {
              "ghsa": "GHSA-9ggj-r5px-674v",
              "severity": "low",
              "published": "2026-10-27T09:08:43Z"
            },
            {
              "ghsa": "GHSA-6gr2-qh89-hxwm",
              "cve": "CVE-2026-50143",
              "severity": "high",
              "published": "2026-05-28T12:11:28Z"
            },
            {
              "ghsa": "GHSA-jwp7-wg77-3w9v",
              "cve": "CVE-2026-46341",
              "severity": "medium",
              "published": "2026-05-13T13:37:52Z"
            }
          ],
          "replies": {
            "sampled": 25,
            "unanswered": 21,
            "medianDays": 0.1
          }
        },
        "updatedAt": "2026-11-18T22:45:57.054523297Z"
      },
      "streak": {
        "days": 20,
        "from": "2026-10-29",
        "last": {
          "kind": "breaking",
          "date": "2026-10-29",
          "what": "v0.20.0 stopped `call-actor` calling Actor MCP tools (`actor:tool` syntax) and removed `output.mcpTools` from `fetch-actor-details`, replaced by `call-actor-mcp-tool` and `fetch-actor-mcp-tool-list`, flagged as breaking",
          "source": "https://github.com/apify/apify-mcp-server/blob/master/CHANGELOG.md"
        },
        "best": 20
      }
    },
    "answer": "Apify MCP Server scores 79 (A) on agent readiness against Scrapling's 68.5 (B), and leads in every scored category.",
    "b": {
      "slug": "scrapling",
      "name": "Scrapling",
      "vendor": "Karim Shoair",
      "vendorUrl": "https://github.com/D4Vinci",
      "company": "github.com-d4vinci",
      "kind": "mcp",
      "category": "web-scrapers",
      "summary": "Scrapling is an open-source Python web scraping library by Karim Shoair, with fast HTTP requests, stealth browsers, adaptive parsing, spiders and a local MCP server of 17 tools for AI agents.",
      "url": "https://www.anchorterminal.com/tools/scrapling",
      "markdownUrl": "https://www.anchorterminal.com/tools/scrapling.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/scrapling.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/scrapling.json",
      "dns": "scrapling.grade.anchorterminal.com",
      "repo": "https://github.com/D4Vinci/Scrapling",
      "license": "BSD-3-Clause",
      "transports": [
        "stdio",
        "streamable-http"
      ],
      "packages": [
        {
          "registry": "pypi",
          "name": "scrapling"
        }
      ],
      "auth": "none",
      "authNotes": "None over stdio. The streamable HTTP transport needs one shared bearer token set with `--auth-token` or `SCRAPLING_MCP_AUTH_TOKEN`, and refuses to start without it unless `--no-auth` is passed. There are no scopes, and rotating the token means restarting the server.",
      "pricing": "free",
      "pricingNotes": "Free and open source under BSD-3-Clause, with no hosted plan. Proxies and CAPTCHA-solving services the README promotes are sold separately by their own vendors.",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the source or docs (checked 2026-11-18). The software is free and runs locally.",
        "endpoints": []
      },
      "toolCount": 17,
      "popularity": {
        "githubStars": 104200,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://scrapling.readthedocs.io",
      "registryName": "io.github.D4Vinci/Scrapling",
      "capabilities": [
        "web.scrape",
        "web.extract",
        "web.crawl",
        "scraping.js-render",
        "scraping.anti-bot",
        "scraping.proxies",
        "browser.control"
      ],
      "tags": [
        "open-source",
        "local",
        "self-hosted",
        "bsd",
        "python",
        "mcp",
        "cli",
        "docker",
        "mcp-registry",
        "agent-skills",
        "no-auth",
        "free",
        "beta"
      ],
      "lastRelease": "2026-11-04",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 68.5,
        "grade": "B",
        "agentReady": false,
        "rank": 380,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 10,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 71,
          "maintenance": 93,
          "payments": 90,
          "reliability": 65,
          "schema": 81,
          "security": 39,
          "transparency": 52
        },
        "assessment": {
          "confidence": "high",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "Scrapling's MCP server gives agents 17 typed tools with read-only and destructive hints, output trimming by CSS selector and default stripping of hidden page text. It is pre-1.0 (0.5.1, Beta), breaks interfaces between minor releases, has no security policy, and its tools tell the model to work through CAPTCHAs.",
        "bestFor": "Agents that need to fetch and drive pages locally, including JavaScript-heavy or bot-protected ones, without a hosted scraping bill.",
        "strengths": [
          "Every one of the 17 MCP tools has typed Pydantic inputs, enum values for formats and wait states, and readOnlyHint or destructiveHint annotations",
          "The HTTP transport refuses to start without a bearer token unless `--no-auth` is passed, and the docs explain why",
          "Hidden elements, zero-width characters, comments and template tags are stripped from page text by default before it reaches the model",
          "BSD-3-Clause, with a dated changelog back to v0.1 on 13 October 2024 and three releases between 23 August and 4 November 2026",
          "`css_selector`, Markdown or text output and cursor-paged network history (1 to 200 records a call) keep responses small"
        ],
        "weaknesses": [
          "Version 0.5.1 with a Beta classifier. v0.4.15, v0.5 and v0.5.1 each carried breaking changes, the last in a patch release",
          "The server instructions and `browser_observe` description tell the model to solve sliders and CAPTCHAs, and the README promotes bypassing Cloudflare Turnstile",
          "No SECURITY.md or disclosure policy in the repository, and no published advisories found",
          "No guard against private or loopback URLs on direct requests. Only redirects to private addresses are blocked, with the `safe` setting",
          "One shared bearer token for the HTTP transport, with no scopes and a restart to rotate it"
        ],
        "agentNotes": [
          "Start with `make_request` and move to `browser_fetch_once` only when the page needs JavaScript or blocks plain HTTP",
          "Pass `css_selector` on fetch tools to cut output. Snapshots need one match or no selector",
          "Read network history with `browser_network_requests` before `close_session`, since closing a session drops it",
          "Check the target site's terms and robots.txt yourself. The MCP tools don't read robots.txt, only the spiders do",
          "If you run the server over HTTP, set `SCRAPLING_MCP_AUTH_TOKEN` and keep it behind TLS. The token travels in clear over plain HTTP"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "high",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 68.5
          }
        ],
        "editorialScores": {
          "ergonomics": 71,
          "maintenance": 93,
          "payments": 90,
          "reliability": 65,
          "schema": 81,
          "security": 39,
          "transparency": 65
        },
        "provenanceScore": 39,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "lastMoved": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "pip install \"scrapling[ai]\" \u0026\u0026 scrapling install",
        "claudeCode": "claude mcp add ScraplingServer -- scrapling-mcp",
        "config": {
          "mcpServers": {
            "ScraplingServer": {
              "command": "scrapling-mcp"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/web.scrape",
        "tool": "https://letme.dev/scrapling"
      },
      "area": "web-data",
      "provenance": {
        "legalEntity": "",
        "domain": "github.com/D4Vinci",
        "domainRegistered": "",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "https://github.com/D4Vinci/Scrapling/blob/main/docs/changelog.md",
        "securityTxt": "none",
        "checked": "2026-11-18",
        "notes": [
          "An individual's open-source project. pyproject.toml names Karim Shoair as author and maintainer, and LICENSE gives the copyright to him (2024). No company is named on the docs site or in the repository.",
          "No terms of service or privacy policy exist for the package or the docs site, which Read the Docs hosts. scrapling.readthedocs.io's robots.txt allows every agent, and the site answers 404 for /llms.txt (read 18 November 2026).",
          "No SECURITY.md or security.txt in the repository."
        ],
        "score": 39
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/scrapling.json",
      "live": {
        "slug": "scrapling",
        "versions": [
          {
            "registry": "mcp-registry",
            "name": "io.github.D4Vinci/Scrapling",
            "version": "0.5.1",
            "seenAt": "2026-11-18T22:45:57.054523297Z"
          }
        ],
        "updatedAt": "2026-11-18T22:45:57.054523297Z"
      }
    },
    "edges": [
      {
        "by": 34,
        "category": "transparency",
        "leads": "apify-mcp",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "MIT (30). Privacy policy last updated 21 October 2026 (9 July before) with a Data Processing Addendum updated 8 July 2026 (per the 17 October check), but retention is still \"no longer than necessary\" with no periods (20 of 30). Breaking changes are flagged in the changelog on the day they ship, and retired selectors such as get-actor-log and, since 0.19.0, source are ignored without an error. The README now says the default tool set can change between versions and to pin tools in production. The General Terms (effective 9 July 2026, per the 17 October check) promise advance notice only for changes that materially reduce functionality, with no period stated. No deprecation policy found (10 of 20). Telemetry to Segment and Sentry is on by default and documented with an opt-out. Since 0.19.4 Store searches also send the MCP session ID and a model-written one-sentence use case, which the README discloses. The policy names the EU and US as the main data locations. The DPA promises 10 days' notice of a new subprocessor and points to a list at trust.apify.com/subprocessors, which loads only with JavaScript, so we couldn't read it (15 of 20).",
          "b": "BSD-3-Clause in LICENSE and the PyPI classifiers (30). No telemetry or usage reporting found in the source. Page traffic goes to the target sites, with optional DNS-over-HTTPS through Cloudflare. There is no privacy statement for the package (15). No deprecation policy. Breaking changes are announced in the release notes with migration guides for v0.5 and the remote-session change (8). Nothing is collected that we could find, but there is no explicit statement on telemetry (12). 30 + 15 + 8 + 12 = 65."
        },
        "scores": {
          "a": 86,
          "b": 52
        }
      },
      {
        "by": 23,
        "category": "security",
        "leads": "apify-mcp",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "OAuth on mcp.apify.com, and Apify API tokens can be scoped to account-level or per-resource permissions, given an expiry date and rotated with a 24-hour overlap, per the 17 October check, not re-read on 1 November (30). The API reference, re-read on 1 November, still accepts the token as a `?token=` query parameter, which it calls less secure, so less 10 (20). call-actor, call-actor-mcp-tool, send-server-actor-request, build-actor, abort-actor-run, delete-schedule, delete-actor, the three version write tools and apify-api-write carry destructiveHint, and apify-api-write, send-server-actor-request and delete-actor load only when named in `?tools=`. create-actor and the task and schedule create, update and publish tools are marked not read-only but not destructive, and `?tools=` can limit a session to read tools. There's no server-side confirmation step (15 of 20). Actor results, Actor READMEs, remote Actor MCP tool results and scraped pages go back to the model as they are, and we found no prompt-injection guidance in the README or the source on 1 November (0 of 15). Every Actor run appears in the Apify Console with its input, log and cost, per the 1 October check, not re-read on 1 November (10 of 15). SOC 2 Type II with the report on request through trust.apify.com, a disclosure policy through security@apify.com, GitHub private vulnerability reporting, and a security.txt re-read on 1 November that is valid until 1 January 2035. Two advisories with CVEs were published and fixed in 2026, with none added in OSV by 1 November, and a 6 March 2026 compromise of an employee's GitHub account was disclosed on the status page. 0.20.0 (29 October) fixed a privately reported flaw where `?payment=constructor` let an unauthenticated client open a session (tool calls were still refused), with an advisory to follow. No bug bounty found (17 of 20).",
          "b": "Read as local software with an optional HTTP transport. stdio needs no credential. Over HTTP the server refuses to start without a token or an explicit `--no-auth`, and accepts one shared bearer token with no scopes, rotated by restarting (15). Annotations let a client gate the destructive tools, and `follow_redirects` defaults to `safe`, which blocks redirects to private addresses. A direct request to localhost or a private address is not refused, and there is no read-only mode (10). Hidden elements, aria-hidden content, zero-width characters, comments and template tags are stripped by default before page text reaches the model, as documented in the MCP guide. The vendor's claim, untested by us (10). Browser sessions record network history the agent and operator can read back. No call log (4). No SECURITY.md, disclosure address or bug bounty in the repository, and GitHub's advisory page couldn't be read (0). 15 + 10 + 10 + 4 + 0 = 39."
        },
        "scores": {
          "a": 62,
          "b": 39
        }
      },
      {
        "by": 21,
        "category": "ergonomics",
        "leads": "apify-mcp",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "14 tools by default and 47 in the README table on 1 November. 0.19.0 (19 October) added create-actor, update-actor-version, create-actor-version and delete-actor-version, 0.19.4 send-server-actor-request (by name only), and 0.20.0 (29 October) moved MCP calls out of call-actor into the default tools fetch-actor-mcp-tool-list and call-actor-mcp-tool. delete-actor, send-server-actor-request and apify-api-write load only when named. `?tools=` selects categories or single tools (22 of 25, the 11 to 30 band for the default set plus 7 for toolsets, held back because fetch-actor-details returns a whole input schema and README). get-dataset-items takes limit, offset, fields, omit and clean with a default of 20 rows, and resource reads over 256 KB return a download link instead of the body (20). Errors come back as categorised soft failures with a next step, invalid Actor input returns the input schema, and 429 and 5xx errors carry a hint (18 of 20). Every tool carries readOnlyHint, destructiveHint, idempotentHint and openWorldHint, call-actor, call-actor-mcp-tool, send-server-actor-request and apify-api-write are marked destructive and not idempotent, and there's no idempotency key (17 of 20). Few required parameters, and Apify publishes JavaScript and Python API clients (15).",
          "b": "17 tools, and v0.5 and v0.5.1 both shortened the descriptions. No toolsets or read-only subset (15). `css_selector` narrows fetch output, extraction can be Markdown, HTML, text or an ARIA snapshot with search, `main_content_only` is on by default, and network history is paged with a cursor and a limit of 1 to 200 (18). Failures from bad input, the browser and curl come back as tool errors with the message, which the v0.5 notes say were made clearer. No error codes an agent can branch on (12). Every tool carries annotations, read-only for fetches and lists and destructive for actions, JavaScript and state files. HTTP requests retry three times by default with a one-second wait (17). Only `url` is required for a fetch, with schema defaults. One language, Python, plus a CLI and Docker (9). 15 + 18 + 12 + 17 + 9 = 71."
        },
        "scores": {
          "a": 92,
          "b": 71
        }
      },
      {
        "by": 11,
        "category": "schema",
        "leads": "apify-mcp",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "Every helper tool has a zod input schema, and Actor tools take the Actor's own input schema, capped at 256 KB (25). Docs pages are served as Markdown (docs.apify.com/api/v2.md) and the API has a public OpenAPI file at docs.apify.com/api/openapi.json (10). Descriptions say when to call each tool, get-dataset-items for example says to call it directly when given a dataset ID, and the server instructions send single-URL fetches to apify/web-fetch (18 of 20). Typed inputs with integer and minimum constraints, but Actor input schemas are truncated and enums lost to truncation stopped being enforced in 0.15.6 (12 of 15). Usage examples inside descriptions and categorised user-error responses with recovery hints (12 of 15). git-cliff changelog with breaking changes flagged (0.19.0 and 0.20.0 included) and tagged releases (15).",
          "b": "Read from the server source (scrapling/core/ai/server.py) and docs/ai/mcp-server.md in the repository. Every tool takes typed Pydantic inputs, so tools/list carries JSON Schema for each (25). No llms.txt in the repository, and scrapling.readthedocs.io answers 404 for /llms.txt. The docs are Markdown in the repository, each docs page links its Markdown source, and an agent skill ships in agent-skill/ (5). Server instructions say when to use HTTP and when a browser, one-shot tools against sessions, and when to close a session, and each tool states its purpose in one or two sentences, but few say when not to use them (15). Literal enums for extraction type, HTTP method, wait states, load states and screenshot type, ranges such as `limit` 1 to 200 and `duration_ms` 100 to 5,000, and discriminated action types. Proxy and cookie fields take free dictionaries (12). The MCP guide has example prompts and setup for each client. Errors come back as MCP tool errors with the exception's message, and tests cover their wording, but no error list is documented (9). A dated changelog for every release from v0.1 (13 October 2024) to v0.5.1 (4 November 2026), and the server reports its version (15). 25 + 5 + 15 + 12 + 9 + 15 = 81."
        },
        "scores": {
          "a": 92,
          "b": 81
        }
      },
      {
        "by": 10,
        "category": "reliability",
        "leads": "apify-mcp",
        "name": "Reliability",
        "reasons": {
          "a": "Atlassian Statuspage at status.apify.com, history read from its RSS feed on 1 November (20). No incident since 22 September. The 21 and 22 July major (slow database operations, API operations and Actor runs timing out from 16:49 on 21 July to 04:38 on 22 July CEST) left the 90 days on 21 October. Five incidents in the 90 days from 3 August, none read as major. 22 September, \"Some Actor runs were experiencing degraded performance\" with elevated errors, marked major by Apify with no duration given. 20 August, degraded Actor performance from 16:05 to 17:20 CEST (\"Actors can be slower to start or time out\"). 13 and 14 August, the SHADER datacenter proxy group. 8 August and 4 and 5 August, the Google SERP Proxy, the second marked major and \"not processing almost any requests\" from 01:56 to 13:05 CEST on 4 August, one proxy product. Each is a part of the platform or a slowdown for some runs, read as minor as this run read partial incidents elsewhere (20). Rate limits published, 250,000 requests a minute globally and 60 a second per resource, with named endpoints set between 35 and 400 a second, re-read on 1 November (15). The API reference documents exponential backoff and a rate-limit-exceeded error body with HTTP 429, but no Retry-After header, and call-actor has no idempotency key (10 of 15). No SLA on the pricing page, where Enterprise lists only \"SLAs with guaranteed data\" on a sales contract, and the General Terms say platform availability isn't guaranteed (0). The hosted server is in production use, not labelled beta (10). 20+20+15+10+0+10 = 75.",
          "b": "Read on the local-software lines, since the MCP server runs on the user's machine over stdio or a self-run HTTP port. Installs from PyPI (`scrapling[ai]`) or Docker (`pyd4vinci/scrapling`, `ghcr.io/d4vinci/scrapling`), with Python 3.10 or later and 3.10 to 3.13 in the classifiers (20). tests.yml runs tox on Python 3.10 to 3.13 on macOS for pushes and pull requests to main and dev, and the repository holds about 1,390 test functions, 19 test files for the MCP tools among them. Run results on GitHub couldn't be read on 18 November, so passing on main is unchecked (15 of 25). Five issues were open on 18 November 2026 against 104,200 stars, the oldest from 24 October 2025, and two of them had a reply. The v0.5.1 notes credit fixes from outside contributors and close reported issues such as #540 (20 of 25). Breaking changes carry a warning and a migration guide in the changelog, but v0.5.1 broke remote browser connections in a patch release (10 of 15). Version 0.5.1 with a Development Status 4 Beta classifier (0). 20 + 15 + 20 + 10 + 0 = 65."
        },
        "scores": {
          "a": 75,
          "b": 65
        }
      },
      {
        "by": 9,
        "category": "payments",
        "leads": "apify-mcp",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "x402 on Apify's own domains. agi.apify.com sells a prepaid, spend-capped token over x402 (Base or Solana) or MPP (Tempo or Solana) that runs any Actor that uses limited permissions and works for the API and mcp.apify.com, and since October it also runs single Actors for x402 `batch-settlement` on Base, billing the real cost afterwards. The direct `?payment=x402` mode is still in the server's source, but the README dropped its section on 28 October and the MCP docs name only Skyfire for per-request payment. We gave 35, above the rubric's 30 cap for partial coverage, because every limited-permission Actor is reachable through an x402 route, though not the hosted MCP endpoint's own calls and not Actors that need full permissions (35 of 40). Compute units at $0.20, $0.16 and $0.13 by plan, published without a login and re-read on 1 November (20). Free plan with $5 of usage a month, \"No credit card is required\" (20). An agent with a wallet gets a token with no signup (20). Re-scored on 13 November 2026 for the new payments rubric: the protocol's 35 of 40 is 8.75 of 10, and the other lines' 60 is 90 at 30 each, so 95 is 99.",
          "b": "Free, self-hosted software under BSD-3-Clause with nothing to buy, read with the self-hosted rule. No payment protocol (0), nothing to price (30), free (30), no signup or key (30). 0 + 30 + 30 + 30 = 90."
        },
        "scores": {
          "a": 99,
          "b": 90
        }
      }
    ],
    "facts": [
      {
        "a": "MCP server",
        "b": "MCP server",
        "name": "Kind"
      },
      {
        "a": "Apify",
        "b": "Karim Shoair",
        "name": "Vendor"
      },
      {
        "a": "https://mcp.apify.com",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "stdio, Streamable HTTP",
        "b": "stdio, Streamable HTTP",
        "name": "Transports"
      },
      {
        "a": "OAuth or key",
        "b": "None",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Free",
        "name": "Pricing"
      },
      {
        "a": "yes, from $1/call",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "MIT",
        "b": "BSD-3-Clause",
        "name": "Licence"
      },
      {
        "a": "47",
        "b": "17",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "no",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "com.apify/apify-mcp-server",
        "b": "io.github.D4Vinci/Scrapling",
        "name": "MCP registry"
      },
      {
        "a": "2026-10-29",
        "b": "2026-11-04",
        "name": "Last release"
      },
      {
        "a": "2026-07-09",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "2026-07-09",
        "b": "no document linked",
        "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": "not found in the text",
        "b": "not read yet",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "8.6k stars, 15k npm/wk",
        "b": "104k stars",
        "name": "Popularity"
      },
      {
        "a": "3.4/5 (8)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Apify MCP Server scores 79 (A) on agent readiness against Scrapling's 68.5 (B), and leads in every scored category.",
        "question": "Which is better for AI agents, Apify MCP Server or Scrapling?"
      },
      {
        "answer": "Apify MCP Server takes an API key or an OAuth sign-in. Scrapling needs no key. An agent can also pay Apify MCP Server per call over x402, with no account.",
        "question": "Do Apify MCP Server and Scrapling need an API key?"
      },
      {
        "answer": "Apify MCP Server has a hosted endpoint at https://mcp.apify.com. Scrapling runs on your own machine, with no hosted endpoint listed.",
        "question": "Can an agent call Apify MCP Server and Scrapling without installing anything?"
      },
      {
        "answer": "Yes. Apify MCP Server is open source (MIT). Scrapling is open source (BSD-3-Clause).",
        "question": "Are Apify MCP Server and Scrapling open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 75 against 65",
          "Schema \u0026 documentation, 92 against 81",
          "Agent ergonomics, 92 against 71",
          "Security \u0026 auth, 62 against 39",
          "Payments \u0026 pricing, 99 against 90",
          "Transparency \u0026 trust, 86 against 52"
        ],
        "also": [
          "Agent-ready, a grade of BB or better",
          "An agent can pay per call over x402, with no account",
          "A hosted endpoint, with nothing to install"
        ],
        "goodFor": "Best when the job matches an existing Actor (Google Maps, social profiles, e-commerce, SERP) and the agent can wait seconds to minutes for a run.",
        "slug": "apify-mcp",
        "watchFor": "0.19.0 and 0.20.0 (19 and 29 October 2026) changed tool behaviour with breaking changes flagged only on release day"
      },
      {
        "aheadOn": null,
        "also": [
          "No key needed to call it",
          "No incidents deducted, where Apify MCP Server loses 5 points for them"
        ],
        "goodFor": "Agents that need to fetch and drive pages locally, including JavaScript-heavy or bot-protected ones, without a hosted scraping bill.",
        "slug": "scrapling",
        "watchFor": "Version 0.5.1 with a Beta classifier. v0.4.15, v0.5 and v0.5.1 each carried breaking changes, the last in a patch release"
      }
    ],
    "history": {
      "apify-mcp": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 0.5,
          "from": 78.5,
          "fromGrade": "A",
          "to": 79,
          "toGrade": "A"
        },
        {
          "causes": [
            "time"
          ],
          "date": "2026-11-01",
          "delta": 2,
          "from": 76.5,
          "fromGrade": "BB",
          "to": 78.5,
          "toGrade": "A"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-08",
          "delta": -0.1,
          "from": 76.6,
          "fromGrade": "BB",
          "to": 76.5,
          "toGrade": "BB"
        }
      ],
      "scrapling": [
        {
          "causes": [
            "evidence"
          ],
          "date": "2026-11-18",
          "delta": 3.3,
          "from": 65.2,
          "fromGrade": "B",
          "to": 68.5,
          "toGrade": "B"
        }
      ]
    },
    "job": {
      "capability": "web.crawl",
      "name": "Crawling"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-browseract.json",
        "title": "Apify MCP Server vs BrowserAct",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-browseract"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-jina-reader.json",
        "title": "Apify MCP Server vs Jina Reader",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-jina-reader"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-microlink.json",
        "title": "Apify MCP Server vs Microlink",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-microlink"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-oxylabs-web-scraper.json",
        "title": "Apify MCP Server vs Oxylabs Web Scraper API",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-oxylabs-web-scraper"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrape-do.json",
        "title": "Apify MCP Server vs Scrape.do",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrape-do"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapingant.json",
        "title": "Apify MCP Server vs ScrapingAnt",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapingant"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapingbee.json",
        "title": "Apify MCP Server vs ScrapingBee",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapingbee"
      },
      {
        "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/apify-mcp-vs-webscraping-ai.json",
        "title": "Apify MCP Server vs WebScraping.AI",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-webscraping-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-zenrows.json",
        "title": "Apify MCP Server vs ZenRows",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-zenrows"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-zyte.json",
        "title": "Apify MCP Server vs Zyte API",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-zyte"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bright-data-vs-scrapling.json",
        "title": "Bright Data vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/bright-data-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/browseract-vs-scrapling.json",
        "title": "BrowserAct vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/browseract-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/context-dev-vs-scrapling.json",
        "title": "Context.dev vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/context-dev-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crawl4ai-vs-scrapling.json",
        "title": "Crawl4AI vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/crawl4ai-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crw-vs-scrapling.json",
        "title": "fastCRW vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/crw-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/decodo-vs-scrapling.json",
        "title": "Decodo Web Data API vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/decodo-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jina-reader-vs-scrapling.json",
        "title": "Jina Reader vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/jina-reader-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microlink-vs-scrapling.json",
        "title": "Microlink vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/microlink-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/olostep-vs-scrapling.json",
        "title": "Olostep vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/olostep-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/outcrawl-vs-scrapling.json",
        "title": "Outcrawl vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/outcrawl-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/oxylabs-web-scraper-vs-scrapling.json",
        "title": "Oxylabs Web Scraper API vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/oxylabs-web-scraper-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrape-do-vs-scrapling.json",
        "title": "Scrape.do vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scrape-do-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapegraphai-vs-scrapling.json",
        "title": "ScrapeGraphAI vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scrapegraphai-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapeless-vs-scrapling.json",
        "title": "Scrapeless vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scrapeless-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scraperapi-vs-scrapling.json",
        "title": "ScraperAPI vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scraperapi-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapewise-vs-scrapling.json",
        "title": "Scrapewise vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scrapewise-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapfly-vs-scrapling.json",
        "title": "Scrapfly vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scrapfly-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapingant-vs-scrapling.json",
        "title": "ScrapingAnt vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scrapingant-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapingbee-vs-scrapling.json",
        "title": "ScrapingBee vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scrapingbee-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapingdog-vs-scrapling.json",
        "title": "Scrapingdog vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scrapingdog-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapling-vs-spider-cloud.json",
        "title": "Scrapling vs Spider",
        "url": "https://www.anchorterminal.com/compare/scrapling-vs-spider-cloud"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapling-vs-webscraping-ai.json",
        "title": "Scrapling vs WebScraping.AI",
        "url": "https://www.anchorterminal.com/compare/scrapling-vs-webscraping-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapling-vs-zenrows.json",
        "title": "Scrapling vs ZenRows",
        "url": "https://www.anchorterminal.com/compare/scrapling-vs-zenrows"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapling-vs-zyte.json",
        "title": "Scrapling vs Zyte API",
        "url": "https://www.anchorterminal.com/compare/scrapling-vs-zyte"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffbot-vs-scrapling.json",
        "title": "Diffbot vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/diffbot-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapling.json",
        "title": "Firecrawl MCP vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nexscope-vs-scrapling.json",
        "title": "Nexscope vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/nexscope-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/qovia-vs-scrapling.json",
        "title": "Qovia vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/qovia-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapeatlas-vs-scrapling.json",
        "title": "ScrapeAtlas vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scrapeatlas-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapling-vs-soldfetch.json",
        "title": "Scrapling vs SoldFetch",
        "url": "https://www.anchorterminal.com/compare/scrapling-vs-soldfetch"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-bright-data.json",
        "title": "Apify MCP Server vs Bright Data",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-bright-data"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-context-dev.json",
        "title": "Apify MCP Server vs Context.dev",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-context-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-crawl4ai.json",
        "title": "Apify MCP Server vs Crawl4AI",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-crawl4ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-crw.json",
        "title": "Apify MCP Server vs fastCRW",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-crw"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-decodo.json",
        "title": "Apify MCP Server vs Decodo Web Data API",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-decodo"
      },
      {
        "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"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-firecrawl-mcp.json",
        "title": "Apify MCP Server vs Firecrawl MCP",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-firecrawl-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-jevcrawl.json",
        "title": "Apify MCP Server vs jevcrawl",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-jevcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-olostep.json",
        "title": "Apify MCP Server vs Olostep",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-olostep"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-outcrawl.json",
        "title": "Apify MCP Server vs Outcrawl",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-outcrawl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapegraphai.json",
        "title": "Apify MCP Server vs ScrapeGraphAI",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapegraphai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapeless.json",
        "title": "Apify MCP Server vs Scrapeless",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapeless"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-scraperapi.json",
        "title": "Apify MCP Server vs ScraperAPI",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-scraperapi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapewise.json",
        "title": "Apify MCP Server vs Scrapewise",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapewise"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapfly.json",
        "title": "Apify MCP Server vs Scrapfly",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapfly"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-spider-cloud.json",
        "title": "Apify MCP Server vs Spider",
        "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-spider-cloud"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jevcrawl-vs-scrapling.json",
        "title": "jevcrawl vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/jevcrawl-vs-scrapling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scrapeops-vs-scrapling.json",
        "title": "ScrapeOps Proxy API Aggregator vs Scrapling",
        "url": "https://www.anchorterminal.com/compare/scrapeops-vs-scrapling"
      }
    ],
    "panel": null,
    "scores": [
      {
        "apify-mcp": 75,
        "by": 10,
        "edge": "apify-mcp",
        "key": "reliability",
        "name": "Reliability",
        "scrapling": 65,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "apify-mcp": 92,
        "by": 11,
        "edge": "apify-mcp",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "scrapling": 81,
        "weight": 13
      },
      {
        "apify-mcp": 92,
        "by": 21,
        "edge": "apify-mcp",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "scrapling": 71,
        "weight": 13
      },
      {
        "apify-mcp": 62,
        "by": 23,
        "edge": "apify-mcp",
        "key": "security",
        "name": "Security \u0026 auth",
        "scrapling": 39,
        "weight": 14
      },
      {
        "apify-mcp": 99,
        "by": 9,
        "edge": "apify-mcp",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "scrapling": 90,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "apify-mcp": 95,
        "by": 2,
        "edge": "apify-mcp",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "scrapling": 93,
        "weight": 7
      },
      {
        "apify-mcp": 86,
        "by": 34,
        "edge": "apify-mcp",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "scrapling": 52,
        "weight": 7
      }
    ],
    "summary": "Apify MCP Server scores 79 (A) on agent readiness against Scrapling's 68.5 (B), and leads in every scored category. Both do crawling. Apify MCP Server accepts x402. Scrapling doesn't.",
    "tasks": null,
    "tutorials": [
      {
        "title": "Extract a small website dataset with Apify MCP",
        "tool": "apify-mcp",
        "url": "https://www.anchorterminal.com/tutorials/apify-mcp/"
      }
    ],
    "verdicts": {
      "apify-mcp": "x402 on Apify's own domains, a prepaid token from agi.apify.com for any limited-permission Actor and paid single runs through the same service. Tool names and defaults still change between 0.x releases, with breaking changes flagged only on release day.",
      "scrapling": "Scrapling's MCP server gives agents 17 typed tools with read-only and destructive hints, output trimming by CSS selector and default stripping of hidden page text. It is pre-1.0 (0.5.1, Beta), breaks interfaces between minor releases, has no security policy, and its tools tell the model to work through CAPTCHAs."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapling",
    "json": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapling.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapling.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapling.min.md"
  },
  "markdown": "Apify MCP Server scores 79 (A) on agent readiness against Scrapling's 68.5 (B), and leads in every scored category. Both do crawling. Apify MCP Server accepts x402. Scrapling doesn't.\n\n- Apify MCP Server: grade A, 79/100, rank #41 of 1557. Markdown https://www.anchorterminal.com/tools/apify-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/apify-mcp.json\n- Scrapling: grade B, 68.5/100, rank #380 of 1557. Markdown https://www.anchorterminal.com/tools/scrapling.md · JSON https://www.anchorterminal.com/api/v1/tools/scrapling.json\n- Best web scraping and crawling APIs for AI agents: https://www.anchorterminal.com/best/web-scrapers/index.md\n- All 567 scrapers comparisons: https://www.anchorterminal.com/compare/web-scrapers/index.md\n\n## Which one, for what\n\n### Apify MCP Server (A)\n\nGood for: Best when the job matches an existing Actor (Google Maps, social profiles, e-commerce, SERP) and the agent can wait seconds to minutes for a run.\n\nAhead on:\n- Reliability, 75 against 65\n- Schema \u0026 documentation, 92 against 81\n- Agent ergonomics, 92 against 71\n- Security \u0026 auth, 62 against 39\n- Payments \u0026 pricing, 99 against 90\n- Transparency \u0026 trust, 86 against 52\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- An agent can pay per call over x402, with no account\n- A hosted endpoint, with nothing to install\n\nWatch for: 0.19.0 and 0.20.0 (19 and 29 October 2026) changed tool behaviour with breaking changes flagged only on release day\n\n### Scrapling (B)\n\nGood for: Agents that need to fetch and drive pages locally, including JavaScript-heavy or bot-protected ones, without a hosted scraping bill.\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where Apify MCP Server loses 5 points for them\n\nWatch for: Version 0.5.1 with a Beta classifier. v0.4.15, v0.5 and v0.5.1 each carried breaking changes, the last in a patch release\n\n\n## Why the edge\n\n### Transparency \u0026 trust: Apify MCP Server +34\n\n- Apify MCP Server (86): MIT (30). Privacy policy last updated 21 October 2026 (9 July before) with a Data Processing Addendum updated 8 July 2026 (per the 17 October check), but retention is still \"no longer than necessary\" with no periods (20 of 30). Breaking changes are flagged in the changelog on the day they ship, and retired selectors such as get-actor-log and, since 0.19.0, source are ignored without an error. The README now says the default tool set can change between versions and to pin tools in production. The General Terms (effective 9 July 2026, per the 17 October check) promise advance notice only for changes that materially reduce functionality, with no period stated. No deprecation policy found (10 of 20). Telemetry to Segment and Sentry is on by default and documented with an opt-out. Since 0.19.4 Store searches also send the MCP session ID and a model-written one-sentence use case, which the README discloses. The policy names the EU and US as the main data locations. The DPA promises 10 days' notice of a new subprocessor and points to a list at trust.apify.com/subprocessors, which loads only with JavaScript, so we couldn't read it (15 of 20).\n- Scrapling (52): BSD-3-Clause in LICENSE and the PyPI classifiers (30). No telemetry or usage reporting found in the source. Page traffic goes to the target sites, with optional DNS-over-HTTPS through Cloudflare. There is no privacy statement for the package (15). No deprecation policy. Breaking changes are announced in the release notes with migration guides for v0.5 and the remote-session change (8). Nothing is collected that we could find, but there is no explicit statement on telemetry (12). 30 + 15 + 8 + 12 = 65.\n\n### Security \u0026 auth: Apify MCP Server +23\n\n- Apify MCP Server (62): OAuth on mcp.apify.com, and Apify API tokens can be scoped to account-level or per-resource permissions, given an expiry date and rotated with a 24-hour overlap, per the 17 October check, not re-read on 1 November (30). The API reference, re-read on 1 November, still accepts the token as a `?token=` query parameter, which it calls less secure, so less 10 (20). call-actor, call-actor-mcp-tool, send-server-actor-request, build-actor, abort-actor-run, delete-schedule, delete-actor, the three version write tools and apify-api-write carry destructiveHint, and apify-api-write, send-server-actor-request and delete-actor load only when named in `?tools=`. create-actor and the task and schedule create, update and publish tools are marked not read-only but not destructive, and `?tools=` can limit a session to read tools. There's no server-side confirmation step (15 of 20). Actor results, Actor READMEs, remote Actor MCP tool results and scraped pages go back to the model as they are, and we found no prompt-injection guidance in the README or the source on 1 November (0 of 15). Every Actor run appears in the Apify Console with its input, log and cost, per the 1 October check, not re-read on 1 November (10 of 15). SOC 2 Type II with the report on request through trust.apify.com, a disclosure policy through security@apify.com, GitHub private vulnerability reporting, and a security.txt re-read on 1 November that is valid until 1 January 2035. Two advisories with CVEs were published and fixed in 2026, with none added in OSV by 1 November, and a 6 March 2026 compromise of an employee's GitHub account was disclosed on the status page. 0.20.0 (29 October) fixed a privately reported flaw where `?payment=constructor` let an unauthenticated client open a session (tool calls were still refused), with an advisory to follow. No bug bounty found (17 of 20).\n- Scrapling (39): Read as local software with an optional HTTP transport. stdio needs no credential. Over HTTP the server refuses to start without a token or an explicit `--no-auth`, and accepts one shared bearer token with no scopes, rotated by restarting (15). Annotations let a client gate the destructive tools, and `follow_redirects` defaults to `safe`, which blocks redirects to private addresses. A direct request to localhost or a private address is not refused, and there is no read-only mode (10). Hidden elements, aria-hidden content, zero-width characters, comments and template tags are stripped by default before page text reaches the model, as documented in the MCP guide. The vendor's claim, untested by us (10). Browser sessions record network history the agent and operator can read back. No call log (4). No SECURITY.md, disclosure address or bug bounty in the repository, and GitHub's advisory page couldn't be read (0). 15 + 10 + 10 + 4 + 0 = 39.\n\n### Agent ergonomics: Apify MCP Server +21\n\n- Apify MCP Server (92): 14 tools by default and 47 in the README table on 1 November. 0.19.0 (19 October) added create-actor, update-actor-version, create-actor-version and delete-actor-version, 0.19.4 send-server-actor-request (by name only), and 0.20.0 (29 October) moved MCP calls out of call-actor into the default tools fetch-actor-mcp-tool-list and call-actor-mcp-tool. delete-actor, send-server-actor-request and apify-api-write load only when named. `?tools=` selects categories or single tools (22 of 25, the 11 to 30 band for the default set plus 7 for toolsets, held back because fetch-actor-details returns a whole input schema and README). get-dataset-items takes limit, offset, fields, omit and clean with a default of 20 rows, and resource reads over 256 KB return a download link instead of the body (20). Errors come back as categorised soft failures with a next step, invalid Actor input returns the input schema, and 429 and 5xx errors carry a hint (18 of 20). Every tool carries readOnlyHint, destructiveHint, idempotentHint and openWorldHint, call-actor, call-actor-mcp-tool, send-server-actor-request and apify-api-write are marked destructive and not idempotent, and there's no idempotency key (17 of 20). Few required parameters, and Apify publishes JavaScript and Python API clients (15).\n- Scrapling (71): 17 tools, and v0.5 and v0.5.1 both shortened the descriptions. No toolsets or read-only subset (15). `css_selector` narrows fetch output, extraction can be Markdown, HTML, text or an ARIA snapshot with search, `main_content_only` is on by default, and network history is paged with a cursor and a limit of 1 to 200 (18). Failures from bad input, the browser and curl come back as tool errors with the message, which the v0.5 notes say were made clearer. No error codes an agent can branch on (12). Every tool carries annotations, read-only for fetches and lists and destructive for actions, JavaScript and state files. HTTP requests retry three times by default with a one-second wait (17). Only `url` is required for a fetch, with schema defaults. One language, Python, plus a CLI and Docker (9). 15 + 18 + 12 + 17 + 9 = 71.\n\n### Schema \u0026 documentation: Apify MCP Server +11\n\n- Apify MCP Server (92): Every helper tool has a zod input schema, and Actor tools take the Actor's own input schema, capped at 256 KB (25). Docs pages are served as Markdown (docs.apify.com/api/v2.md) and the API has a public OpenAPI file at docs.apify.com/api/openapi.json (10). Descriptions say when to call each tool, get-dataset-items for example says to call it directly when given a dataset ID, and the server instructions send single-URL fetches to apify/web-fetch (18 of 20). Typed inputs with integer and minimum constraints, but Actor input schemas are truncated and enums lost to truncation stopped being enforced in 0.15.6 (12 of 15). Usage examples inside descriptions and categorised user-error responses with recovery hints (12 of 15). git-cliff changelog with breaking changes flagged (0.19.0 and 0.20.0 included) and tagged releases (15).\n- Scrapling (81): Read from the server source (scrapling/core/ai/server.py) and docs/ai/mcp-server.md in the repository. Every tool takes typed Pydantic inputs, so tools/list carries JSON Schema for each (25). No llms.txt in the repository, and scrapling.readthedocs.io answers 404 for /llms.txt. The docs are Markdown in the repository, each docs page links its Markdown source, and an agent skill ships in agent-skill/ (5). Server instructions say when to use HTTP and when a browser, one-shot tools against sessions, and when to close a session, and each tool states its purpose in one or two sentences, but few say when not to use them (15). Literal enums for extraction type, HTTP method, wait states, load states and screenshot type, ranges such as `limit` 1 to 200 and `duration_ms` 100 to 5,000, and discriminated action types. Proxy and cookie fields take free dictionaries (12). The MCP guide has example prompts and setup for each client. Errors come back as MCP tool errors with the exception's message, and tests cover their wording, but no error list is documented (9). A dated changelog for every release from v0.1 (13 October 2024) to v0.5.1 (4 November 2026), and the server reports its version (15). 25 + 5 + 15 + 12 + 9 + 15 = 81.\n\n### Reliability: Apify MCP Server +10\n\n- Apify MCP Server (75): Atlassian Statuspage at status.apify.com, history read from its RSS feed on 1 November (20). No incident since 22 September. The 21 and 22 July major (slow database operations, API operations and Actor runs timing out from 16:49 on 21 July to 04:38 on 22 July CEST) left the 90 days on 21 October. Five incidents in the 90 days from 3 August, none read as major. 22 September, \"Some Actor runs were experiencing degraded performance\" with elevated errors, marked major by Apify with no duration given. 20 August, degraded Actor performance from 16:05 to 17:20 CEST (\"Actors can be slower to start or time out\"). 13 and 14 August, the SHADER datacenter proxy group. 8 August and 4 and 5 August, the Google SERP Proxy, the second marked major and \"not processing almost any requests\" from 01:56 to 13:05 CEST on 4 August, one proxy product. Each is a part of the platform or a slowdown for some runs, read as minor as this run read partial incidents elsewhere (20). Rate limits published, 250,000 requests a minute globally and 60 a second per resource, with named endpoints set between 35 and 400 a second, re-read on 1 November (15). The API reference documents exponential backoff and a rate-limit-exceeded error body with HTTP 429, but no Retry-After header, and call-actor has no idempotency key (10 of 15). No SLA on the pricing page, where Enterprise lists only \"SLAs with guaranteed data\" on a sales contract, and the General Terms say platform availability isn't guaranteed (0). The hosted server is in production use, not labelled beta (10). 20+20+15+10+0+10 = 75.\n- Scrapling (65): Read on the local-software lines, since the MCP server runs on the user's machine over stdio or a self-run HTTP port. Installs from PyPI (`scrapling[ai]`) or Docker (`pyd4vinci/scrapling`, `ghcr.io/d4vinci/scrapling`), with Python 3.10 or later and 3.10 to 3.13 in the classifiers (20). tests.yml runs tox on Python 3.10 to 3.13 on macOS for pushes and pull requests to main and dev, and the repository holds about 1,390 test functions, 19 test files for the MCP tools among them. Run results on GitHub couldn't be read on 18 November, so passing on main is unchecked (15 of 25). Five issues were open on 18 November 2026 against 104,200 stars, the oldest from 24 October 2025, and two of them had a reply. The v0.5.1 notes credit fixes from outside contributors and close reported issues such as #540 (20 of 25). Breaking changes carry a warning and a migration guide in the changelog, but v0.5.1 broke remote browser connections in a patch release (10 of 15). Version 0.5.1 with a Development Status 4 Beta classifier (0). 20 + 15 + 20 + 10 + 0 = 65.\n\n### Payments \u0026 pricing: Apify MCP Server +9\n\n- Apify MCP Server (99): x402 on Apify's own domains. agi.apify.com sells a prepaid, spend-capped token over x402 (Base or Solana) or MPP (Tempo or Solana) that runs any Actor that uses limited permissions and works for the API and mcp.apify.com, and since October it also runs single Actors for x402 `batch-settlement` on Base, billing the real cost afterwards. The direct `?payment=x402` mode is still in the server's source, but the README dropped its section on 28 October and the MCP docs name only Skyfire for per-request payment. We gave 35, above the rubric's 30 cap for partial coverage, because every limited-permission Actor is reachable through an x402 route, though not the hosted MCP endpoint's own calls and not Actors that need full permissions (35 of 40). Compute units at $0.20, $0.16 and $0.13 by plan, published without a login and re-read on 1 November (20). Free plan with $5 of usage a month, \"No credit card is required\" (20). An agent with a wallet gets a token with no signup (20). Re-scored on 13 November 2026 for the new payments rubric: the protocol's 35 of 40 is 8.75 of 10, and the other lines' 60 is 90 at 30 each, so 95 is 99.\n- Scrapling (90): Free, self-hosted software under BSD-3-Clause with nothing to buy, read with the self-hosted rule. No payment protocol (0), nothing to price (30), free (30), no signup or key (30). 0 + 30 + 30 + 30 = 90.\n\n## Score by category\n\n| Category | Weight | Apify MCP Server | Scrapling | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 75 | 65 | Apify MCP Server +10 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 92 | 81 | Apify MCP Server +11 |\n| Agent ergonomics | 13% | 92 | 71 | Apify MCP Server +21 |\n| Security \u0026 auth | 14% | 62 | 39 | Apify MCP Server +23 |\n| Payments \u0026 pricing | 10% | 99 | 90 | Apify MCP Server +9 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 95 | 93 | Apify MCP Server +2 |\n| Transparency \u0026 trust | 7% | 86 | 52 | Apify MCP Server +34 |\n| Negative events | ≤15 | -5 | 0 | |\n| **Total** | | **79 · A** | **68.5 · B** | |\n\n## Facts side by side\n\n| Fact | Apify MCP Server | Scrapling |\n| --- | --- | --- |\n| Kind | MCP server | MCP server |\n| Vendor | Apify | Karim Shoair |\n| Hosted endpoint | `https://mcp.apify.com` | no (local only) |\n| Transports | stdio, Streamable HTTP | stdio, Streamable HTTP |\n| Auth | OAuth or key | None |\n| Pricing | Freemium | Free |\n| x402 | yes, from $1/call | no |\n| Licence | MIT | BSD-3-Clause |\n| Tools exposed | 47 | 17 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| MCP registry | `com.apify/apify-mcp-server` | `io.github.D4Vinci/Scrapling` |\n| Last release | 2026-10-29 | 2026-11-04 |\n| Terms last updated | 2026-07-09 | no document linked |\n| Privacy policy last updated | 2026-07-09 | no document linked |\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 | not found in the text | not read yet |\n| Popularity | 8.6k stars, 15k npm/wk | 104k stars |\n| Agent reviews | 3.4/5 (8) | none |\n\n## How the scores have moved\n\n### Apify MCP Server\n\n- +0.5 on 13 November 2026: checklist\n- +2.0 on 1 November 2026 (BB to A): time\n- -0.1 on 8 October 2026: checklist\n\n### Scrapling\n\n- +3.3 on 18 November 2026: new evidence\n\n## Verdicts\n\n**Apify MCP Server.** x402 on Apify's own domains, a prepaid token from agi.apify.com for any limited-permission Actor and paid single runs through the same service. Tool names and defaults still change between 0.x releases, with breaking changes flagged only on release day.\n\n**Scrapling.** Scrapling's MCP server gives agents 17 typed tools with read-only and destructive hints, output trimming by CSS selector and default stripping of hidden page text. It is pre-1.0 (0.5.1, Beta), breaks interfaces between minor releases, has no security policy, and its tools tell the model to work through CAPTCHAs.\n\n## Before you call either\n\n### Apify MCP Server\n\n1. Call fetch-actor-details before call-actor to get the input schema and the price\n2. Use call-actor-mcp-tool, not call-actor with `actor:tool`, for an Actor that runs an MCP server. List its tools first with fetch-actor-mcp-tool-list\n3. Read results with get-dataset-items and set `fields` and `limit`. The default is 20 rows\n4. Buy an AGI token to pay without an account. Tokens last 14 days, unused balance isn't refunded, and Actors needing full permissions refuse them\n5. Pin `?tools=` in production. The default tool set changes between versions\n\n### Scrapling\n\n1. Start with `make_request` and move to `browser_fetch_once` only when the page needs JavaScript or blocks plain HTTP\n2. Pass `css_selector` on fetch tools to cut output. Snapshots need one match or no selector\n3. Read network history with `browser_network_requests` before `close_session`, since closing a session drops it\n4. Check the target site's terms and robots.txt yourself. The MCP tools don't read robots.txt, only the spiders do\n5. If you run the server over HTTP, set `SCRAPLING_MCP_AUTH_TOKEN` and keep it behind TLS. The token travels in clear over plain HTTP\n\n## Tutorials\n\n- [Extract a small website dataset with Apify MCP](https://www.anchorterminal.com/tutorials/apify-mcp/), for Apify MCP Server\n\n## Questions\n\n### Which is better for AI agents, Apify MCP Server or Scrapling?\n\nApify MCP Server scores 79 (A) on agent readiness against Scrapling's 68.5 (B), and leads in every scored category.\n\n### Do Apify MCP Server and Scrapling need an API key?\n\nApify MCP Server takes an API key or an OAuth sign-in. Scrapling needs no key. An agent can also pay Apify MCP Server per call over x402, with no account.\n\n### Can an agent call Apify MCP Server and Scrapling without installing anything?\n\nApify MCP Server has a hosted endpoint at https://mcp.apify.com. Scrapling runs on your own machine, with no hosted endpoint listed.\n\n### Are Apify MCP Server and Scrapling open source?\n\nYes. Apify MCP Server is open source (MIT). Scrapling is open source (BSD-3-Clause).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/apify-mcp-vs-scrapling.json, and with the fewest tokens: https://www.anchorterminal.com/compare/apify-mcp-vs-scrapling.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"apify-mcp\", \"b\": \"scrapling\"}`. From a terminal: `anchor compare apify-mcp scrapling`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/apify-mcp.json and https://www.anchorterminal.com/api/v1/tools/scrapling.json\n\n## Other comparisons with Apify MCP Server or Scrapling\n\n- [Apify MCP Server vs BrowserAct](https://www.anchorterminal.com/compare/apify-mcp-vs-browseract.md)\n- [Apify MCP Server vs Jina Reader](https://www.anchorterminal.com/compare/apify-mcp-vs-jina-reader.md)\n- [Apify MCP Server vs Microlink](https://www.anchorterminal.com/compare/apify-mcp-vs-microlink.md)\n- [Apify MCP Server vs Oxylabs Web Scraper API](https://www.anchorterminal.com/compare/apify-mcp-vs-oxylabs-web-scraper.md)\n- [Apify MCP Server vs Scrape.do](https://www.anchorterminal.com/compare/apify-mcp-vs-scrape-do.md)\n- [Apify MCP Server vs ScrapingAnt](https://www.anchorterminal.com/compare/apify-mcp-vs-scrapingant.md)\n- [Apify MCP Server vs ScrapingBee](https://www.anchorterminal.com/compare/apify-mcp-vs-scrapingbee.md)\n- [Apify MCP Server vs Scrapingdog](https://www.anchorterminal.com/compare/apify-mcp-vs-scrapingdog.md)\n- [Apify MCP Server vs WebScraping.AI](https://www.anchorterminal.com/compare/apify-mcp-vs-webscraping-ai.md)\n- [Apify MCP Server vs ZenRows](https://www.anchorterminal.com/compare/apify-mcp-vs-zenrows.md)\n- [Apify MCP Server vs Zyte API](https://www.anchorterminal.com/compare/apify-mcp-vs-zyte.md)\n- [Bright Data vs Scrapling](https://www.anchorterminal.com/compare/bright-data-vs-scrapling.md)\n- [BrowserAct vs Scrapling](https://www.anchorterminal.com/compare/browseract-vs-scrapling.md)\n- [Context.dev vs Scrapling](https://www.anchorterminal.com/compare/context-dev-vs-scrapling.md)\n- [Crawl4AI vs Scrapling](https://www.anchorterminal.com/compare/crawl4ai-vs-scrapling.md)\n- [fastCRW vs Scrapling](https://www.anchorterminal.com/compare/crw-vs-scrapling.md)\n- [Decodo Web Data API vs Scrapling](https://www.anchorterminal.com/compare/decodo-vs-scrapling.md)\n- [Jina Reader vs Scrapling](https://www.anchorterminal.com/compare/jina-reader-vs-scrapling.md)\n- [Microlink vs Scrapling](https://www.anchorterminal.com/compare/microlink-vs-scrapling.md)\n- [Olostep vs Scrapling](https://www.anchorterminal.com/compare/olostep-vs-scrapling.md)\n- [Outcrawl vs Scrapling](https://www.anchorterminal.com/compare/outcrawl-vs-scrapling.md)\n- [Oxylabs Web Scraper API vs Scrapling](https://www.anchorterminal.com/compare/oxylabs-web-scraper-vs-scrapling.md)\n- [Scrape.do vs Scrapling](https://www.anchorterminal.com/compare/scrape-do-vs-scrapling.md)\n- [ScrapeGraphAI vs Scrapling](https://www.anchorterminal.com/compare/scrapegraphai-vs-scrapling.md)\n- [Scrapeless vs Scrapling](https://www.anchorterminal.com/compare/scrapeless-vs-scrapling.md)\n- [ScraperAPI vs Scrapling](https://www.anchorterminal.com/compare/scraperapi-vs-scrapling.md)\n- [Scrapewise vs Scrapling](https://www.anchorterminal.com/compare/scrapewise-vs-scrapling.md)\n- [Scrapfly vs Scrapling](https://www.anchorterminal.com/compare/scrapfly-vs-scrapling.md)\n- [ScrapingAnt vs Scrapling](https://www.anchorterminal.com/compare/scrapingant-vs-scrapling.md)\n- [ScrapingBee vs Scrapling](https://www.anchorterminal.com/compare/scrapingbee-vs-scrapling.md)\n- [Scrapingdog vs Scrapling](https://www.anchorterminal.com/compare/scrapingdog-vs-scrapling.md)\n- [Scrapling vs Spider](https://www.anchorterminal.com/compare/scrapling-vs-spider-cloud.md)\n- [Scrapling vs WebScraping.AI](https://www.anchorterminal.com/compare/scrapling-vs-webscraping-ai.md)\n- [Scrapling vs ZenRows](https://www.anchorterminal.com/compare/scrapling-vs-zenrows.md)\n- [Scrapling vs Zyte API](https://www.anchorterminal.com/compare/scrapling-vs-zyte.md)\n- [Diffbot vs Scrapling](https://www.anchorterminal.com/compare/diffbot-vs-scrapling.md)\n- [Firecrawl MCP vs Scrapling](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-scrapling.md)\n- [Nexscope vs Scrapling](https://www.anchorterminal.com/compare/nexscope-vs-scrapling.md)\n- [Qovia vs Scrapling](https://www.anchorterminal.com/compare/qovia-vs-scrapling.md)\n- [ScrapeAtlas vs Scrapling](https://www.anchorterminal.com/compare/scrapeatlas-vs-scrapling.md)\n- [Scrapling vs SoldFetch](https://www.anchorterminal.com/compare/scrapling-vs-soldfetch.md)\n- [Apify MCP Server vs Bright Data](https://www.anchorterminal.com/compare/apify-mcp-vs-bright-data.md)\n- [Apify MCP Server vs Context.dev](https://www.anchorterminal.com/compare/apify-mcp-vs-context-dev.md)\n- [Apify MCP Server vs Crawl4AI](https://www.anchorterminal.com/compare/apify-mcp-vs-crawl4ai.md)\n- [Apify MCP Server vs fastCRW](https://www.anchorterminal.com/compare/apify-mcp-vs-crw.md)\n- [Apify MCP Server vs Decodo Web Data API](https://www.anchorterminal.com/compare/apify-mcp-vs-decodo.md)\n- [Apify MCP Server vs Diffbot](https://www.anchorterminal.com/compare/apify-mcp-vs-diffbot.md)\n- [Apify MCP Server vs Firecrawl MCP](https://www.anchorterminal.com/compare/apify-mcp-vs-firecrawl-mcp.md)\n- [Apify MCP Server vs jevcrawl](https://www.anchorterminal.com/compare/apify-mcp-vs-jevcrawl.md)\n- [Apify MCP Server vs Olostep](https://www.anchorterminal.com/compare/apify-mcp-vs-olostep.md)\n- [Apify MCP Server vs Outcrawl](https://www.anchorterminal.com/compare/apify-mcp-vs-outcrawl.md)\n- [Apify MCP Server vs ScrapeGraphAI](https://www.anchorterminal.com/compare/apify-mcp-vs-scrapegraphai.md)\n- [Apify MCP Server vs Scrapeless](https://www.anchorterminal.com/compare/apify-mcp-vs-scrapeless.md)\n- [Apify MCP Server vs ScraperAPI](https://www.anchorterminal.com/compare/apify-mcp-vs-scraperapi.md)\n- [Apify MCP Server vs Scrapewise](https://www.anchorterminal.com/compare/apify-mcp-vs-scrapewise.md)\n- [Apify MCP Server vs Scrapfly](https://www.anchorterminal.com/compare/apify-mcp-vs-scrapfly.md)\n- [Apify MCP Server vs Spider](https://www.anchorterminal.com/compare/apify-mcp-vs-spider-cloud.md)\n- [jevcrawl vs Scrapling](https://www.anchorterminal.com/compare/jevcrawl-vs-scrapling.md)\n- [ScrapeOps Proxy API Aggregator vs Scrapling](https://www.anchorterminal.com/compare/scrapeops-vs-scrapling.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": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "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": "Apify MCP Server vs Scrapling",
        "url": ""
      }
    ],
    "description": "Apify scores 79 (A) to Scrapling's 68.5 (B) for crawling. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Apify MCP Server A 79",
      "Scrapling B 68.5",
      "scores"
    ],
    "h1": "Apify MCP Server vs Scrapling",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/apify-mcp-vs-scrapling",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Apify vs Scrapling for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/apify-mcp-vs-scrapling"
  },
  "tokens": {
    "markdown": 6750,
    "slim": 1130
  },
  "version": 1
}
