{
  "fixes": {
    "slug": "apify-mcp",
    "name": "Apify MCP Server",
    "listing": "https://www.anchorterminal.com/tools/apify-mcp",
    "markdown": "# Fix list: Apify MCP Server\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/apify-mcp, the October 2026 research run, assessed 1 October 2026. Grade A, 78.6 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Apify MCP Server: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Reliability, 65 out of 100, up to 7 more on the total\n\nWhy it scored 65: Atlassian Statuspage at status.apify.com, history read from its RSS feed (20). Nine incidents since 1 July 2026. One major inside the last 90 days, slow database operations that left API operations and Actor runs timing out from 16:49 on 21 July to 04:38 on 22 July CEST, about 12 hours (10). The others were degraded Actor starts on 20 August (just over 2 hours), Standby errors on 26 July and SERP or proxy slowdowns. Rate limits published, 250,000 requests a minute globally and 60 a second per resource, 200 or 400 on some endpoints (15). The API reference documents exponential backoff from 500 ms and a rate-limit-exceeded error body, but no Retry-After header, and call-actor has no idempotency key (10 of 15). No SLA on the pricing page (0). The hosted server is in production use, not labelled beta (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 2. Security \u0026 auth, 62 out of 100, up to 6.7 more on the total\n\nWhy it scored 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 (30). The API also accepts the same token as a `token` query parameter, a documented option, so less 10 (20). delete-schedule, call-actor and other write tools carry destructiveHint, and `?tools=` can limit a session to read tools, but there's no server-side confirmation step (15 of 20). Actor results, Actor READMEs and scraped pages go back to the model as they are, and we found no prompt-injection guidance in the README, the server instructions or the docs we read (0 of 15). Every Actor run appears in the Apify Console with its input, log and cost (10 of 15). SOC 2 Type II, a disclosure policy through security@apify.com, GitHub private vulnerability reporting, and a valid security.txt per the 26 September check. No bug bounty found (17 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 3. Schema \u0026 documentation, 92 out of 100, up to 1.3 more on the total\n\nWhy it scored 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 and tagged releases (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 4. Agent ergonomics, 92 out of 100, up to 1.3 more on the total\n\nWhy it scored 92: 12 tools by default and 35 in the README table, with `?tools=` selecting categories or single tools (22 of 25, the 11 to 30 band 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, and invalid Actor input returns the input schema since 0.15.2 (18 of 20). Every tool carries readOnlyHint, destructiveHint, idempotentHint and openWorldHint, and call-actor is marked destructive and not idempotent, with no idempotency key (17 of 20). Few required parameters, and Apify publishes JavaScript and Python API clients (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 5. Transparency \u0026 trust, 88 out of 100, up to 1.1 more on the total\n\nMade of editorial 75, provenance 100.\n\nWhy it scored 88: MIT (30). Privacy policy updated 9 July 2026 with a Data Processing Addendum, but retention is '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 are ignored without an error. No deprecation policy or advance notice found (10 of 20). Telemetry to Segment and Sentry is on by default and documented with an opt-out, and the policy names the EU and US as the main data locations, with no subprocessor list (15 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\n## 6. Payments \u0026 pricing, 95 out of 100, up to 0.6 more on the total\n\nWhy it scored 95: x402 in two forms on Apify's own domains. `mcp.apify.com?payment=x402` takes per-run USDC on Base for Pay Per Event Actors (not Standby Actors), and agi.apify.com sells a prepaid, spend-capped token over x402 or MPP that works for any Actor and the API. We gave 35, above the rubric's 30 cap for partial coverage, because every Actor is reachable through an x402 route even though direct per-call payment covers Pay Per Event Actors only (35 of 40). Compute units at $0.20, $0.16 and $0.13 by plan, published without a login (20). Free plan with $5 of usage a month, 'No credit card required' (20). An agent with a wallet gets a token with no signup (20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 7. Maintenance \u0026 community, 95 out of 100, up to 0.4 more on the total\n\nWhy it scored 95: v0.17.1 on 2026-09-30, with 0.17.2 in the unreleased changelog (30). 18 tagged releases between 21 July and 30 September (20). The open issues on the first page date from 26 July to 6 August and are mostly maintainer follow-ups, with fixes landing weekly. Reply times weren't visible to us (20 of 25). com.apify/apify-mcp-server in the official registry under a DNS-verified namespace (15). CI runs code checks, integration and conformance tests and npm and MCPB smoke tests (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- -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).\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- Issue and pull request reply times, which the issues page didn't show us.\n- Whether an SLA exists on Enterprise contracts; none is published.\n- Whether the July 21 and 22 outage affected mcp.apify.com itself or only Actor runs behind it.\n\n## Weaknesses\n\n- API and Actor runs timed out for about 12 hours on 21 and 22 July 2026\n- No prompt-injection guidance for scraped content or third-party Actor READMEs\n- Telemetry and Sentry on by default\n- Direct x402 and Skyfire cover Pay Per Event Actors only, not Standby Actors\n- No SLA published for any self-serve plan\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Call fetch-actor-details before call-actor to get the input schema and the price\n- Use apify--web-fetch for one known URL and apify--rag-web-browser for search and read\n- Read results with get-dataset-items and set `fields` and `limit`. The default is 20 rows\n- Buy an AGI token for anything that isn't a Pay Per Event Actor. Direct `?payment=x402` refuses the rest\n- Ask for `get-actor-run-log`, not `get-actor-log`. The old name is ignored without an error\n\n## What the review panel asked for\n\n- Direct x402 for Standby\n- Errors for retired names\n- Idempotency key on call-actor\n- an error for retired tool names\n- a deprecation window before renames\n- Return an error for retired tool names\n- An idempotency key on `call-actor`\n- A `Retry-After` header on 429\n- drop query-string tokens\n- confirmation on destructive tools\n- state whether failed runs are billed\n- Actor quality signals\n- errors for retired names\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "A",
    "score": 78.6,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 65,
        "maxGain": 7,
        "reason": "Atlassian Statuspage at status.apify.com, history read from its RSS feed (20). Nine incidents since 1 July 2026. One major inside the last 90 days, slow database operations that left API operations and Actor runs timing out from 16:49 on 21 July to 04:38 on 22 July CEST, about 12 hours (10). The others were degraded Actor starts on 20 August (just over 2 hours), Standby errors on 26 July and SERP or proxy slowdowns. Rate limits published, 250,000 requests a minute globally and 60 a second per resource, 200 or 400 on some endpoints (15). The API reference documents exponential backoff from 500 ms and a rate-limit-exceeded error body, but no Retry-After header, and call-actor has no idempotency key (10 of 15). No SLA on the pricing page (0). The hosted server is in production use, not labelled beta (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 62,
        "maxGain": 6.7,
        "reason": "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 (30). The API also accepts the same token as a `token` query parameter, a documented option, so less 10 (20). delete-schedule, call-actor and other write tools carry destructiveHint, and `?tools=` can limit a session to read tools, but there's no server-side confirmation step (15 of 20). Actor results, Actor READMEs and scraped pages go back to the model as they are, and we found no prompt-injection guidance in the README, the server instructions or the docs we read (0 of 15). Every Actor run appears in the Apify Console with its input, log and cost (10 of 15). SOC 2 Type II, a disclosure policy through security@apify.com, GitHub private vulnerability reporting, and a valid security.txt per the 26 September check. No bug bounty found (17 of 20).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 92,
        "maxGain": 1.3,
        "reason": "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 and tagged releases (15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 92,
        "maxGain": 1.3,
        "reason": "12 tools by default and 35 in the README table, with `?tools=` selecting categories or single tools (22 of 25, the 11 to 30 band 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, and invalid Actor input returns the input schema since 0.15.2 (18 of 20). Every tool carries readOnlyHint, destructiveHint, idempotentHint and openWorldHint, and call-actor is marked destructive and not idempotent, with no idempotency key (17 of 20). Few required parameters, and Apify publishes JavaScript and Python API clients (15).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 88,
        "maxGain": 1.1,
        "reason": "MIT (30). Privacy policy updated 9 July 2026 with a Data Processing Addendum, but retention is '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 are ignored without an error. No deprecation policy or advance notice found (10 of 20). Telemetry to Segment and Sentry is on by default and documented with an opt-out, and the policy names the EU and US as the main data locations, with no subprocessor list (15 of 20).",
        "blend": "editorial 75, provenance 100",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 95,
        "maxGain": 0.6,
        "reason": "x402 in two forms on Apify's own domains. `mcp.apify.com?payment=x402` takes per-run USDC on Base for Pay Per Event Actors (not Standby Actors), and agi.apify.com sells a prepaid, spend-capped token over x402 or MPP that works for any Actor and the API. We gave 35, above the rubric's 30 cap for partial coverage, because every Actor is reachable through an x402 route even though direct per-call payment covers Pay Per Event Actors only (35 of 40). Compute units at $0.20, $0.16 and $0.13 by plan, published without a login (20). Free plan with $5 of usage a month, 'No credit card required' (20). An agent with a wallet gets a token with no signup (20).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 95,
        "maxGain": 0.4,
        "reason": "v0.17.1 on 2026-09-30, with 0.17.2 in the unreleased changelog (30). 18 tagged releases between 21 July and 30 September (20). The open issues on the first page date from 26 July to 6 August and are mostly maintainer follow-ups, with fixes landing weekly. Reply times weren't visible to us (20 of 25). com.apify/apify-mcp-server in the official registry under a DNS-verified namespace (15). CI runs code checks, integration and conformance tests and npm and MCPB smoke tests (10).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      }
    ],
    "deductions": [
      "-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)."
    ],
    "unchecked": [
      "Issue and pull request reply times, which the issues page didn't show us.",
      "Whether an SLA exists on Enterprise contracts; none is published.",
      "Whether the July 21 and 22 outage affected mcp.apify.com itself or only Actor runs behind it."
    ],
    "weaknesses": [
      "API and Actor runs timed out for about 12 hours on 21 and 22 July 2026",
      "No prompt-injection guidance for scraped content or third-party Actor READMEs",
      "Telemetry and Sentry on by default",
      "Direct x402 and Skyfire cover Pay Per Event Actors only, not Standby Actors",
      "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 apify--web-fetch for one known URL and apify--rag-web-browser for search and read",
      "Read results with get-dataset-items and set `fields` and `limit`. The default is 20 rows",
      "Buy an AGI token for anything that isn't a Pay Per Event Actor. Direct `?payment=x402` refuses the rest",
      "Ask for `get-actor-run-log`, not `get-actor-log`. The old name is ignored without an error"
    ],
    "requests": [
      {
        "text": "Direct x402 for Standby",
        "reviews": 1
      },
      {
        "text": "Errors for retired names",
        "reviews": 1
      },
      {
        "text": "Idempotency key on call-actor",
        "reviews": 1
      },
      {
        "text": "an error for retired tool names",
        "reviews": 1
      },
      {
        "text": "a deprecation window before renames",
        "reviews": 1
      },
      {
        "text": "Return an error for retired tool names",
        "reviews": 1
      },
      {
        "text": "An idempotency key on `call-actor`",
        "reviews": 1
      },
      {
        "text": "A `Retry-After` header on 429",
        "reviews": 1
      },
      {
        "text": "drop query-string tokens",
        "reviews": 1
      },
      {
        "text": "confirmation on destructive tools",
        "reviews": 1
      },
      {
        "text": "state whether failed runs are billed",
        "reviews": 1
      },
      {
        "text": "Actor quality signals",
        "reviews": 1
      },
      {
        "text": "errors for retired names",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}