{
  "fixes": {
    "slug": "microsoft-learn-mcp",
    "name": "Microsoft Learn MCP Server",
    "listing": "https://www.anchorterminal.com/tools/microsoft-learn-mcp",
    "markdown": "# Fix list: Microsoft Learn MCP Server\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/microsoft-learn-mcp, the October 2026 research run, assessed 1 October 2026. Grade D, 48.1 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 Microsoft Learn 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, 20 out of 100, up to 16 more on the total\n\nWhy it scored 20: Scored as a hosted MCP server. We found no status page for Microsoft Learn or this endpoint (0), so there's no readable incident history (5). The FAQ says the free endpoint has rate limits but gives no numbers, and the overview, developer reference and release notes, re-read on 2 October, give none either (0). Throttling and 429 behaviour aren't documented, and Microsoft's own CLI in the repository has no throttling handling, only a tool-list refresh and a session reset. The best-practices page says to refresh `tools/list` and retry after a 400 or 404, which is safe-retry guidance for schema changes, and every tool is a read (5). No SLA (0). Generally available since 7 November 2025 per the release notes (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. Schema \u0026 documentation, 57 out of 100, up to 7 more on the total\n\nWhy it scored 57: The server is closed source and our fetch tools couldn't call `tools/list`, so we graded the tool surface from the README, which lists typed parameters for all three tools. 20 of 25, since we couldn't confirm the live JSON Schema. No llms.txt found. The README is Markdown and the docs pages are HTML (5). The README table gives one line of purpose per tool, and the repository's three agent skills and a suggested system prompt say when to use each (12). Inputs are `query` and `url` strings plus an optional `language` string with no listed values (6). Configuration examples for about twenty clients and a troubleshooting table. No documented error responses beyond 405 (6). A release-notes page with seven dated entries. Microsoft says the tool surface is dynamic and not versioned (8).\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## 3. Security \u0026 auth, 60 out of 100, up to 7 more on the total\n\nWhy it scored 60: No credentials at all, so nothing to leak or scope (20). All three tools are reads (15). Results come from Microsoft's own documentation and code samples, which the README says is the only source (10). No per-call visibility for the caller, since there's no account (0). MSRC reporting with a 24-hour response target in SECURITY.md and Microsoft's bug bounty programme. microsoft.com's security.txt was past its Expires date per the 30 September check (15).\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## 4. Agent ergonomics, 58 out of 100, up to 6.8 more on the total\n\nWhy it scored 58: Three tools, which the README describes in one line each. We couldn't measure the live definitions (25). `maxTokenBudget` on the endpoint URL truncates search results to a token budget. `microsoft_docs_fetch` always returns the whole page and nothing pages (10). Errors aren't documented beyond the 400 or 404 refresh rule and a 405 for browsers (5). Every tool is a read and safe to repeat. We couldn't check whether `readOnlyHint` is set (8). One required parameter per tool and no auth. A CLI on npm, no SDKs (10).\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. Maintenance \u0026 community, 28 out of 100, up to 6.3 more on the total\n\nWhy it scored 28: The last dated release-notes entry for the server is the plugin release on 23 March 2026, 192 days before the run date, and the overview page (updated 22 May 2026) says server updates are announced there (0). The repository's @microsoft/learn-cli 1.0.0 shipped on 4 September 2026, but that's the CLI, not the server. No server entries in the last 90 days (0). Eight open issues, the oldest from June 2025. #100 got a documentation fix on 2 September 2026 and is still open. Questions go to the GitHub repository (8). Listed in the official MCP registry as com.microsoft/microsoft-learn-mcp 1.0.0 under Microsoft's domain namespace (15). The CLI has Dependabot updates (the latest on 10 September 2026), a vitest suite and a validation workflow. The server's own health isn't visible (5).\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## 6. Payments \u0026 pricing, 60 out of 100, up to 5 more on the total\n\nWhy it scored 60: Nothing to buy, so no payment protocol (0). Free, stated in public (20). No account or card (20). An agent connects with no signup or key (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. Transparency \u0026 trust, 57 out of 100, up to 3.8 more on the total\n\nMade of editorial 28, provenance 85.\n\nWhy it scored 57: The server is closed. The repository's code is MIT and its docs CC-BY-4.0, and the Learn terms of use are linked (15). We found no statement of what the endpoint logs or keeps. The FAQ, the overview and the developer reference are silent, and only Microsoft's general privacy statement applies. The overview says the index holds public documentation only, refreshed in full once a day (10). No deprecation policy, and Microsoft says tools can be added, renamed or changed at any time (0). No subprocessors or data locations stated for this service (3).\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\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Status page: not found (0 of 10)\n- security.txt: published but past its Expires date (5 of 10)\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- unchecked: the live `tools/list` definitions, their size and whether `readOnlyHint` is set. Our shell can't reach learn.microsoft.com, WebFetch can't make MCP calls, and the repository's tests use made-up tools. Glama shows the same three tools with one-line descriptions and no annotations, but doesn't date its scan, so we didn't score from it\n- unchecked: what a throttled call returns. Microsoft publishes no number on the FAQ, overview, developer reference or release notes, so the limit itself scores as absent\n- What the endpoint logs about queries and for how long, which none of the four Microsoft pages state\n- Whether the server changed after 23 March 2026 without a release-notes entry. Microsoft says updates go in the release notes, and there's been none since\n\n## Weaknesses\n\n- No status page, and the FAQ admits rate limits without giving numbers\n- Microsoft says tools can change at any time and doesn't version them\n- No statement of what the endpoint logs or keeps\n- `microsoft_docs_fetch` returns whole pages with no size control\n- Microsoft content only\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- Append `?maxTokenBudget=2000` to the endpoint URL to cap search results; it doesn't affect fetch\n- Call `microsoft_docs_search` first and fetch only the one or two URLs that matter, because fetch returns the full page\n- Re-read `tools/list` after any 400 or 404; Microsoft changes tools without versioning them\n- Pass `language` to `microsoft_code_sample_search` when you want samples in one language\n\n## What the review panel asked for\n\n- publish the full tool definitions\n- document error responses\n- endpoint data-handling statement\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": "D",
    "score": 48.1,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 20,
        "maxGain": 16,
        "reason": "Scored as a hosted MCP server. We found no status page for Microsoft Learn or this endpoint (0), so there's no readable incident history (5). The FAQ says the free endpoint has rate limits but gives no numbers, and the overview, developer reference and release notes, re-read on 2 October, give none either (0). Throttling and 429 behaviour aren't documented, and Microsoft's own CLI in the repository has no throttling handling, only a tool-list refresh and a session reset. The best-practices page says to refresh `tools/list` and retry after a 400 or 404, which is safe-retry guidance for schema changes, and every tool is a read (5). No SLA (0). Generally available since 7 November 2025 per the release notes (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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 57,
        "maxGain": 7,
        "reason": "The server is closed source and our fetch tools couldn't call `tools/list`, so we graded the tool surface from the README, which lists typed parameters for all three tools. 20 of 25, since we couldn't confirm the live JSON Schema. No llms.txt found. The README is Markdown and the docs pages are HTML (5). The README table gives one line of purpose per tool, and the repository's three agent skills and a suggested system prompt say when to use each (12). Inputs are `query` and `url` strings plus an optional `language` string with no listed values (6). Configuration examples for about twenty clients and a troubleshooting table. No documented error responses beyond 405 (6). A release-notes page with seven dated entries. Microsoft says the tool surface is dynamic and not versioned (8).",
        "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": "security",
        "name": "Security \u0026 auth",
        "score": 60,
        "maxGain": 7,
        "reason": "No credentials at all, so nothing to leak or scope (20). All three tools are reads (15). Results come from Microsoft's own documentation and code samples, which the README says is the only source (10). No per-call visibility for the caller, since there's no account (0). MSRC reporting with a 24-hour response target in SECURITY.md and Microsoft's bug bounty programme. microsoft.com's security.txt was past its Expires date per the 30 September check (15).",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 58,
        "maxGain": 6.8,
        "reason": "Three tools, which the README describes in one line each. We couldn't measure the live definitions (25). `maxTokenBudget` on the endpoint URL truncates search results to a token budget. `microsoft_docs_fetch` always returns the whole page and nothing pages (10). Errors aren't documented beyond the 400 or 404 refresh rule and a 405 for browsers (5). Every tool is a read and safe to repeat. We couldn't check whether `readOnlyHint` is set (8). One required parameter per tool and no auth. A CLI on npm, no SDKs (10).",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 28,
        "maxGain": 6.3,
        "reason": "The last dated release-notes entry for the server is the plugin release on 23 March 2026, 192 days before the run date, and the overview page (updated 22 May 2026) says server updates are announced there (0). The repository's @microsoft/learn-cli 1.0.0 shipped on 4 September 2026, but that's the CLI, not the server. No server entries in the last 90 days (0). Eight open issues, the oldest from June 2025. #100 got a documentation fix on 2 September 2026 and is still open. Questions go to the GitHub repository (8). Listed in the official MCP registry as com.microsoft/microsoft-learn-mcp 1.0.0 under Microsoft's domain namespace (15). The CLI has Dependabot updates (the latest on 10 September 2026), a vitest suite and a validation workflow. The server's own health isn't visible (5).",
        "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"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 60,
        "maxGain": 5,
        "reason": "Nothing to buy, so no payment protocol (0). Free, stated in public (20). No account or card (20). An agent connects with no signup or key (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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 57,
        "maxGain": 3.8,
        "reason": "The server is closed. The repository's code is MIT and its docs CC-BY-4.0, and the Learn terms of use are linked (15). We found no statement of what the endpoint logs or keeps. The FAQ, the overview and the developer reference are silent, and only Microsoft's general privacy statement applies. The overview says the index holds public documentation only, refreshed in full once a day (10). No deprecation policy, and Microsoft says tools can be added, renamed or changed at any time (0). No subprocessors or data locations stated for this service (3).",
        "blend": "editorial 28, provenance 85",
        "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"
      }
    ],
    "provenance": [
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "published but past its Expires date",
        "points": 5,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: the live `tools/list` definitions, their size and whether `readOnlyHint` is set. Our shell can't reach learn.microsoft.com, WebFetch can't make MCP calls, and the repository's tests use made-up tools. Glama shows the same three tools with one-line descriptions and no annotations, but doesn't date its scan, so we didn't score from it",
      "unchecked: what a throttled call returns. Microsoft publishes no number on the FAQ, overview, developer reference or release notes, so the limit itself scores as absent",
      "What the endpoint logs about queries and for how long, which none of the four Microsoft pages state",
      "Whether the server changed after 23 March 2026 without a release-notes entry. Microsoft says updates go in the release notes, and there's been none since"
    ],
    "weaknesses": [
      "No status page, and the FAQ admits rate limits without giving numbers",
      "Microsoft says tools can change at any time and doesn't version them",
      "No statement of what the endpoint logs or keeps",
      "`microsoft_docs_fetch` returns whole pages with no size control",
      "Microsoft content only"
    ],
    "agentNotes": [
      "Append `?maxTokenBudget=2000` to the endpoint URL to cap search results; it doesn't affect fetch",
      "Call `microsoft_docs_search` first and fetch only the one or two URLs that matter, because fetch returns the full page",
      "Re-read `tools/list` after any 400 or 404; Microsoft changes tools without versioning them",
      "Pass `language` to `microsoft_code_sample_search` when you want samples in one language"
    ],
    "requests": [
      {
        "text": "publish the full tool definitions",
        "reviews": 1
      },
      {
        "text": "document error responses",
        "reviews": 1
      },
      {
        "text": "endpoint data-handling statement",
        "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"
  }
}