{
  "fixes": {
    "slug": "mapbox",
    "name": "Mapbox APIs + MCP",
    "listing": "https://www.anchorterminal.com/tools/mapbox",
    "markdown": "# Fix list: Mapbox APIs + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/mapbox, the October 2026 research run, assessed 1 October 2026. Grade BB, 75.2 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 Mapbox APIs + MCP: 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. Payments \u0026 pricing, 30 out of 100, up to 8.8 more on the total\n\nWhy it scored 30: No x402, MPP or L402 (0). Per-1,000 prices for every API published without login, $0.75 temporary geocoding, $5 permanent, $2 directions (20). Monthly free allowances per API, 100,000 temporary geocodes and 100,000 directions requests. The docs say accounts are free to create but neither the pricing page nor the billing guide says whether signup needs a card, so we gave half (10). Signup is a browser flow and the hosted MCP needs a browser OAuth step (0).\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## 2. Security \u0026 auth, 71 out of 100, up to 5.1 more on the total\n\nWhy it scored 71: Public and secret tokens with scopes, URL restrictions, one-hour temporary tokens and documented rotation, which earns 30. Less 10 because the REST APIs take the token as the access_token query parameter, and that's the documented way in. The hosted MCP signs in with OAuth instead (20). Public-scope tokens can't change the account, and every MCP tool is read-only (18). Responses are structured place data, partly third-party POI names and attributes, and we found no prompt-injection guidance (7). The local MCP emits OpenTelemetry traces per tool call tagged with the client name. We didn't check per-token usage reporting in the account (8). SOC 2 Type II and SOC 3, a HackerOne bug bounty and a disclosure programme. MCP 0.13.0 on 30 July 2026 fixed a query-parameter injection through directions_tool's exclude field and said so in the public changelog. No security.txt (18).\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. Reliability, 82 out of 100, up to 3.6 more on the total\n\nWhy it scored 82: Atlassian Statuspage at status.mapbox.com with an uptime view (20). The history page renders client-side, so we read the RSS feed. Its newest incident is elevated 206 and 404 errors on the Search Box API on 29 June 2026, about six hours from first update to resolved, which falls just outside the 90 days, and nothing is posted after it (30). Rate limits with numbers, 1,000 geocoding requests a minute by default, and X-Rate-Limit-Interval, -Limit and -Reset headers on responses (15). A 429 on overrun with a reset timestamp to wait for, but no Retry-After and no backoff guidance (10). No SLA on the pricing page or in the API docs (0). The REST APIs are GA, but the MCP server is at 0.14 and its place_details_tool now calls the Places API, which Mapbox labels Public Preview (7).\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## 4. Schema \u0026 documentation, 85 out of 100, up to 2.4 more on the total\n\nWhy it scored 85: No public OpenAPI for the REST APIs, but every MCP tool has a typed Zod input and output schema (20). llms.txt at docs.mapbox.com, per the 30 September check (10). MCP descriptions say when not to use a tool, for example search_and_geocode_tool sends generic place types to category_search_tool and warns that big-box brand plus address queries are unreliable (17). Zod limits and enums, such as q capped at 200 characters after the team found the API rejects 201 (13). An error table per API with 401, 403, 404, 422 and 429 messages, and curl examples throughout (13). Versioned paths (geocode v6) and a dated MCP CHANGELOG.md, but the top-level API changelog's newest entry is 5 November 2021 and current changes sit in per-service pages (12).\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## 5. Agent ergonomics, 88 out of 100, up to 2 more on the total\n\nWhy it scored 88: 29 core MCP tools, so 15, plus 5 back for --enable-tools and --disable-tools on the local server. The docs don't say the hosted endpoint can filter tools (20). limit, types, bbox and proximity on geocoding, and a v6 batch endpoint (18). Documented status codes with messages an agent can act on, such as 'Query exceeded character limit of 200' (17). Every tool carries readOnlyHint true, destructiveHint false and idempotentHint, and 17 offline geometry tools set openWorldHint false (20). Few required parameters and the server elicits a route choice when the client supports it. Official SDKs are JavaScript and the mobile SDKs, with no current official Python client that we found (13).\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## 6. Maintenance \u0026 community, 80 out of 100, up to 1.8 more on the total\n\nWhy it scored 80: MCP server v0.14.0 on 30 July 2026, 63 days before this check, with fixes merged to main up to 17 September (20). Four tags in the last 90 days, v0.12.6, v0.12.7, v0.13.0 and v0.14.0 (20). Commits reference user-reported issues and fixes land within weeks. We couldn't see issue reply times from git (15). Listed in the official MCP registry as io.github.mapbox/mcp-server with an npm package and a remote (15). CI builds and runs the test suite on every push and pull request, and the MCP SDK is at 1.30.0 (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## 7. Transparency \u0026 trust, 86 out of 100, up to 1.2 more on the total\n\nMade of editorial 82, provenance 90.\n\nWhy it scored 86: Closed service with published terms and product terms, plus an MIT-licensed MCP server (20). A DPA, a privacy FAQ that says IP addresses are kept 30 days, and geocoding storage rules that are plain about what can be cached. The terms also let Mapbox build de-identified aggregated data from customer usage (24). An API policy of at least 90 days' emailed notice before an endpoint is deprecated, with dated removals in the changelog, though that changelog stopped in 2021 (18). 22 subprocessors with locations, 14 third-party and 8 affiliates, last updated 4 June 2026 (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\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- security.txt: not found (0 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: whether creating a Mapbox account requires a card\n- unchecked: per-token usage reporting in the account dashboard\n- Whether --enable-tools filtering works on the hosted mcp.mapbox.com endpoint\n- The geocoding docs give both 1,000 and 50 as the v6 batch maximum\n- No SLA found for any self-serve plan. An enterprise SLA may exist under contract\n\n## Weaknesses\n\n- Storing geocodes needs the Permanent tier at $5 per 1,000, about 6.7 times the temporary rate\n- Geocoding results may only be used with a Mapbox map\n- REST calls take the token as the access_token query parameter\n- 29 MCP tools load at once on the hosted endpoint, with filtering documented only for the local server\n- No SLA on the pricing page or in the API docs, and no security.txt\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- Set permanent=true only when the result goes into a database, since it moves the call to the $5 per 1,000 rate\n- Keep search_and_geocode_tool queries under 200 characters, the live limit, not the 256 the API docs state\n- On 429, wait until the X-Rate-Limit-Reset timestamp, since no Retry-After is sent\n- Run the local server with --enable-tools to load only the tools the task needs\n- Use category_search_tool for generic place types like coffee shops, not search_and_geocode_tool\n\n## What the review panel asked for\n\n- One batch number\n- Hosted tool filtering\n- keep the API changelog current\n- a release for the September work\n- correct the limit figures\n- publish an OpenAPI file\n- one batch limit\n- a plain reading of the display terms\n- Add Retry-After to 429s\n- Reconcile the batch maximum\n- header-based token auth\n- State signup card needs\n- Clarify signup card requirement\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": "BB",
    "score": 75.2,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 30,
        "maxGain": 8.8,
        "reason": "No x402, MPP or L402 (0). Per-1,000 prices for every API published without login, $0.75 temporary geocoding, $5 permanent, $2 directions (20). Monthly free allowances per API, 100,000 temporary geocodes and 100,000 directions requests. The docs say accounts are free to create but neither the pricing page nor the billing guide says whether signup needs a card, so we gave half (10). Signup is a browser flow and the hosted MCP needs a browser OAuth step (0).",
        "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": "security",
        "name": "Security \u0026 auth",
        "score": 71,
        "maxGain": 5.1,
        "reason": "Public and secret tokens with scopes, URL restrictions, one-hour temporary tokens and documented rotation, which earns 30. Less 10 because the REST APIs take the token as the access_token query parameter, and that's the documented way in. The hosted MCP signs in with OAuth instead (20). Public-scope tokens can't change the account, and every MCP tool is read-only (18). Responses are structured place data, partly third-party POI names and attributes, and we found no prompt-injection guidance (7). The local MCP emits OpenTelemetry traces per tool call tagged with the client name. We didn't check per-token usage reporting in the account (8). SOC 2 Type II and SOC 3, a HackerOne bug bounty and a disclosure programme. MCP 0.13.0 on 30 July 2026 fixed a query-parameter injection through directions_tool's exclude field and said so in the public changelog. No security.txt (18).",
        "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": "reliability",
        "name": "Reliability",
        "score": 82,
        "maxGain": 3.6,
        "reason": "Atlassian Statuspage at status.mapbox.com with an uptime view (20). The history page renders client-side, so we read the RSS feed. Its newest incident is elevated 206 and 404 errors on the Search Box API on 29 June 2026, about six hours from first update to resolved, which falls just outside the 90 days, and nothing is posted after it (30). Rate limits with numbers, 1,000 geocoding requests a minute by default, and X-Rate-Limit-Interval, -Limit and -Reset headers on responses (15). A 429 on overrun with a reset timestamp to wait for, but no Retry-After and no backoff guidance (10). No SLA on the pricing page or in the API docs (0). The REST APIs are GA, but the MCP server is at 0.14 and its place_details_tool now calls the Places API, which Mapbox labels Public Preview (7).",
        "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": 85,
        "maxGain": 2.4,
        "reason": "No public OpenAPI for the REST APIs, but every MCP tool has a typed Zod input and output schema (20). llms.txt at docs.mapbox.com, per the 30 September check (10). MCP descriptions say when not to use a tool, for example search_and_geocode_tool sends generic place types to category_search_tool and warns that big-box brand plus address queries are unreliable (17). Zod limits and enums, such as q capped at 200 characters after the team found the API rejects 201 (13). An error table per API with 401, 403, 404, 422 and 429 messages, and curl examples throughout (13). Versioned paths (geocode v6) and a dated MCP CHANGELOG.md, but the top-level API changelog's newest entry is 5 November 2021 and current changes sit in per-service pages (12).",
        "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": 88,
        "maxGain": 2,
        "reason": "29 core MCP tools, so 15, plus 5 back for --enable-tools and --disable-tools on the local server. The docs don't say the hosted endpoint can filter tools (20). limit, types, bbox and proximity on geocoding, and a v6 batch endpoint (18). Documented status codes with messages an agent can act on, such as 'Query exceeded character limit of 200' (17). Every tool carries readOnlyHint true, destructiveHint false and idempotentHint, and 17 offline geometry tools set openWorldHint false (20). Few required parameters and the server elicits a route choice when the client supports it. Official SDKs are JavaScript and the mobile SDKs, with no current official Python client that we found (13).",
        "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": 80,
        "maxGain": 1.8,
        "reason": "MCP server v0.14.0 on 30 July 2026, 63 days before this check, with fixes merged to main up to 17 September (20). Four tags in the last 90 days, v0.12.6, v0.12.7, v0.13.0 and v0.14.0 (20). Commits reference user-reported issues and fixes land within weeks. We couldn't see issue reply times from git (15). Listed in the official MCP registry as io.github.mapbox/mcp-server with an npm package and a remote (15). CI builds and runs the test suite on every push and pull request, and the MCP SDK is at 1.30.0 (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"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 86,
        "maxGain": 1.2,
        "reason": "Closed service with published terms and product terms, plus an MIT-licensed MCP server (20). A DPA, a privacy FAQ that says IP addresses are kept 30 days, and geocoding storage rules that are plain about what can be cached. The terms also let Mapbox build de-identified aggregated data from customer usage (24). An API policy of at least 90 days' emailed notice before an endpoint is deprecated, with dated removals in the changelog, though that changelog stopped in 2021 (18). 22 subprocessors with locations, 14 third-party and 8 affiliates, last updated 4 June 2026 (20).",
        "blend": "editorial 82, provenance 90",
        "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": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: whether creating a Mapbox account requires a card",
      "unchecked: per-token usage reporting in the account dashboard",
      "Whether --enable-tools filtering works on the hosted mcp.mapbox.com endpoint",
      "The geocoding docs give both 1,000 and 50 as the v6 batch maximum",
      "No SLA found for any self-serve plan. An enterprise SLA may exist under contract"
    ],
    "weaknesses": [
      "Storing geocodes needs the Permanent tier at $5 per 1,000, about 6.7 times the temporary rate",
      "Geocoding results may only be used with a Mapbox map",
      "REST calls take the token as the access_token query parameter",
      "29 MCP tools load at once on the hosted endpoint, with filtering documented only for the local server",
      "No SLA on the pricing page or in the API docs, and no security.txt"
    ],
    "agentNotes": [
      "Set permanent=true only when the result goes into a database, since it moves the call to the $5 per 1,000 rate",
      "Keep search_and_geocode_tool queries under 200 characters, the live limit, not the 256 the API docs state",
      "On 429, wait until the X-Rate-Limit-Reset timestamp, since no Retry-After is sent",
      "Run the local server with --enable-tools to load only the tools the task needs",
      "Use category_search_tool for generic place types like coffee shops, not search_and_geocode_tool"
    ],
    "requests": [
      {
        "text": "One batch number",
        "reviews": 1
      },
      {
        "text": "Hosted tool filtering",
        "reviews": 1
      },
      {
        "text": "keep the API changelog current",
        "reviews": 1
      },
      {
        "text": "a release for the September work",
        "reviews": 1
      },
      {
        "text": "correct the limit figures",
        "reviews": 1
      },
      {
        "text": "publish an OpenAPI file",
        "reviews": 1
      },
      {
        "text": "one batch limit",
        "reviews": 1
      },
      {
        "text": "a plain reading of the display terms",
        "reviews": 1
      },
      {
        "text": "Add Retry-After to 429s",
        "reviews": 1
      },
      {
        "text": "Reconcile the batch maximum",
        "reviews": 1
      },
      {
        "text": "header-based token auth",
        "reviews": 1
      },
      {
        "text": "State signup card needs",
        "reviews": 1
      },
      {
        "text": "Clarify signup card requirement",
        "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"
  }
}