{
  "fixes": {
    "slug": "google-maps-platform",
    "name": "Google Maps Platform + Grounding Lite MCP",
    "listing": "https://www.anchorterminal.com/tools/google-maps-platform",
    "markdown": "# Fix list: Google Maps Platform + Grounding Lite MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/google-maps-platform, the October 2026 research run, assessed 1 October 2026. Grade B, 68.5 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 Google Maps Platform + Grounding Lite 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, 20 out of 100, up to 10 more on the total\n\nWhy it scored 20: No x402, MPP or L402 (0). Per-1,000 prices for every SKU published without login (20). Monthly free caps per SKU (10,000 Essentials, 5,000 Pro, 1,000 Enterprise), but they need a Cloud billing account with a payment method (0). A person sets up the Cloud project and billing in a browser before the first key exists (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, 67 out of 100, up to 5.8 more on the total\n\nWhy it scored 67: API keys with API restrictions and IP restrictions, documented rotation with an overlap window, and OAuth 2.0 with the maps-platform.mapstools scope for Grounding Lite and service accounts for server traffic, which earns 30. Less 10 because classic Geocoding and Static Maps take the key as the key query parameter (20). A key can be restricted to the APIs it needs, and no agent-facing call writes anything (16). Places and Grounding Lite return reviews and AI-generated place summaries, which are third-party text, and we found no prompt-injection guidance (5). Cloud Monitoring's Metrics Explorer shows usage per key and per API (12). google.com/.well-known/security.txt is valid to 2030 per the 30 September check, and Google runs a public vulnerability reward programme. We couldn't load Google Cloud's SOC 2 page (it answered 429), so certifications aren't counted (14).\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. Maintenance \u0026 community, 50 out of 100, up to 4.4 more on the total\n\nWhy it scored 50: Newest dated API change we found is the Places API (New) note of 6 August 2026 adding entrances and navigationPoints, 56 days before this check (20). Only that one dated entry falls in the last 90 days across the Places and Routes notes we read. Routes' page shows nothing after June 2023, and we didn't read every product's notes (0). Dated release notes, emailed change notices and a paid support route (12). Current generated clients such as @googlemaps/places, but the listed Python library googlemaps last tagged v4.10.0 in January 2023 and the Node services library v3.4.2 in July 2025 (12). The generated clients are built in googleapis' CI. The older libraries say they sit outside the SLA and deprecation policy (6).\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## 4. Schema \u0026 documentation, 77 out of 100, up to 3.7 more on the total\n\nWhy it scored 77: No OpenAPI, but the Places v1, Routes v2, Geocode, Weather and Isochrones contracts are public protobuf definitions in googleapis/googleapis (25). developers.google.com/maps/llms.txt returns 404 and we found no Markdown docs for agents (0). The REST reference explains each field and which SKU a field triggers. We couldn't read the Grounding Lite tool definitions, since the server is closed (12). Enums, required fields and field masks in the protos (13). Request and response examples on each method page, and documented status codes for Geocoding (12). Versioned paths (places v1, routes v2), dated release notes and a deprecations page (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## 5. Reliability, 85 out of 100, up to 3 more on the total\n\nWhy it scored 85: Google Cloud's status dashboard has a Maps Platform section with per-product incident history (20). One incident in the 90 days, on 26 July 2026, a 9 hour 23 minute problem with live traffic data across ten products including Routes, Directions and route optimisation. The APIs answered, but with degraded traffic, so we scored it between the minor and major lines and said so (15). Grounding Lite quotas are 300 queries a minute per project for search, weather and routes and 600 for the resolvers (15). The Geocoding best-practice page gives exponential backoff with a worked example, 100 ms doubling to 5 s, and says which status codes to retry (15). A 99.9 per cent monthly SLA with 10, 25 and 50 per cent credits (10). Grounding Lite, Places (New) and Routes are GA. Only the two resolvers are Experimental (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## 6. Agent ergonomics, 85 out of 100, up to 2.4 more on the total\n\nWhy it scored 85: Grounding Lite has three tools plus two experimental resolvers, and the REST APIs size their responses with X-Goog-FieldMask, which also sets the price (25). pageSize and pageToken on Text Search, includedTypes, locationBias and locationRestriction (20). google.rpc status codes with messages, and Geocoding's OK, UNKNOWN_ERROR, OVER_QUERY_LIMIT and INVALID_REQUEST split into retryable and not (16). Every agent-facing call is a read and the backoff guidance is explicit. We couldn't check MCP annotations on the closed server (14). Official generated clients in many languages, such as @googlemaps/places 3.0.1 on npm, but a missing field mask on Places (New) or Routes is an error rather than a default, which costs a turn (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## 7. Transparency \u0026 trust, 75 out of 100, up to 2.2 more on the total\n\nMade of editorial 65, provenance 85.\n\nWhy it scored 75: Closed service with long, specific terms that were last modified 26 August 2026, and Apache-2.0 client libraries (18). The service terms spell out caching (coordinates 30 days, place IDs exempt, a per-user geocode cache allowed) and Grounding Lite says Maps content isn't cached, stored or used to improve the model. The privacy policy is Google's general one (22). A 12-month deprecation policy and a deprecations page with dates, such as the Heatmap Layer deprecated May 2025 and gone May 2026 (20). Separate EEA terms and regional contracting entities are disclosed. A Maps Platform subprocessor list wasn't at the URL we tried (5).\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- Endpoint on the vendor's domain: maps.googleapis.com is not on google.com (0 of 15)\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 Google Maps Platform is in scope of Google Cloud's SOC 2 and ISO 27001 reports (the compliance page returned 429)\n- unchecked: a Maps Platform subprocessor list and data locations\n- unchecked: MCP annotations and descriptions on the Grounding Lite tools, which are closed source\n- unchecked: release notes for Geocoding and Grounding Lite in the last 90 days\n- The listing's repo and packages point at the older web-services clients (Python last tagged January 2023). The current generated clients are @googlemaps/places and siblings in googleapis/google-cloud-node\n\n## Weaknesses\n\n- A Cloud billing account with a payment method is required before the free caps apply\n- Coordinates may be cached for 30 days at most and only shown on a Google map\n- No llms.txt at developers.google.com/maps\n- Classic Geocoding and Static Maps take the key in the URL\n- Places and Grounding Lite return reviews and AI summaries with no prompt-injection guidance\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- Send X-Goog-FieldMask on every Places (New) and Routes call, since a missing mask is an error and the fields you ask for set the SKU\n- Resolve a name with Text Search and an IDs-only field mask (free), then fetch details for the one place you need\n- Store place IDs, refetch details, and drop cached coordinates after 30 days\n- Retry UNKNOWN_ERROR and OVER_QUERY_LIMIT with exponential backoff, and don't retry INVALID_REQUEST\n- Put Google Maps attribution directly after any answer grounded in Grounding Lite results\n\n## What the review panel asked for\n\n- Free tier without billing\n- Add a no-card free route\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": "B",
    "score": 68.5,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 20,
        "maxGain": 10,
        "reason": "No x402, MPP or L402 (0). Per-1,000 prices for every SKU published without login (20). Monthly free caps per SKU (10,000 Essentials, 5,000 Pro, 1,000 Enterprise), but they need a Cloud billing account with a payment method (0). A person sets up the Cloud project and billing in a browser before the first key exists (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": 67,
        "maxGain": 5.8,
        "reason": "API keys with API restrictions and IP restrictions, documented rotation with an overlap window, and OAuth 2.0 with the maps-platform.mapstools scope for Grounding Lite and service accounts for server traffic, which earns 30. Less 10 because classic Geocoding and Static Maps take the key as the key query parameter (20). A key can be restricted to the APIs it needs, and no agent-facing call writes anything (16). Places and Grounding Lite return reviews and AI-generated place summaries, which are third-party text, and we found no prompt-injection guidance (5). Cloud Monitoring's Metrics Explorer shows usage per key and per API (12). google.com/.well-known/security.txt is valid to 2030 per the 30 September check, and Google runs a public vulnerability reward programme. We couldn't load Google Cloud's SOC 2 page (it answered 429), so certifications aren't counted (14).",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 50,
        "maxGain": 4.4,
        "reason": "Newest dated API change we found is the Places API (New) note of 6 August 2026 adding entrances and navigationPoints, 56 days before this check (20). Only that one dated entry falls in the last 90 days across the Places and Routes notes we read. Routes' page shows nothing after June 2023, and we didn't read every product's notes (0). Dated release notes, emailed change notices and a paid support route (12). Current generated clients such as @googlemaps/places, but the listed Python library googlemaps last tagged v4.10.0 in January 2023 and the Node services library v3.4.2 in July 2025 (12). The generated clients are built in googleapis' CI. The older libraries say they sit outside the SLA and deprecation policy (6).",
        "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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 77,
        "maxGain": 3.7,
        "reason": "No OpenAPI, but the Places v1, Routes v2, Geocode, Weather and Isochrones contracts are public protobuf definitions in googleapis/googleapis (25). developers.google.com/maps/llms.txt returns 404 and we found no Markdown docs for agents (0). The REST reference explains each field and which SKU a field triggers. We couldn't read the Grounding Lite tool definitions, since the server is closed (12). Enums, required fields and field masks in the protos (13). Request and response examples on each method page, and documented status codes for Geocoding (12). Versioned paths (places v1, routes v2), dated release notes and a deprecations page (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": "reliability",
        "name": "Reliability",
        "score": 85,
        "maxGain": 3,
        "reason": "Google Cloud's status dashboard has a Maps Platform section with per-product incident history (20). One incident in the 90 days, on 26 July 2026, a 9 hour 23 minute problem with live traffic data across ten products including Routes, Directions and route optimisation. The APIs answered, but with degraded traffic, so we scored it between the minor and major lines and said so (15). Grounding Lite quotas are 300 queries a minute per project for search, weather and routes and 600 for the resolvers (15). The Geocoding best-practice page gives exponential backoff with a worked example, 100 ms doubling to 5 s, and says which status codes to retry (15). A 99.9 per cent monthly SLA with 10, 25 and 50 per cent credits (10). Grounding Lite, Places (New) and Routes are GA. Only the two resolvers are Experimental (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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 85,
        "maxGain": 2.4,
        "reason": "Grounding Lite has three tools plus two experimental resolvers, and the REST APIs size their responses with X-Goog-FieldMask, which also sets the price (25). pageSize and pageToken on Text Search, includedTypes, locationBias and locationRestriction (20). google.rpc status codes with messages, and Geocoding's OK, UNKNOWN_ERROR, OVER_QUERY_LIMIT and INVALID_REQUEST split into retryable and not (16). Every agent-facing call is a read and the backoff guidance is explicit. We couldn't check MCP annotations on the closed server (14). Official generated clients in many languages, such as @googlemaps/places 3.0.1 on npm, but a missing field mask on Places (New) or Routes is an error rather than a default, which costs a turn (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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 75,
        "maxGain": 2.2,
        "reason": "Closed service with long, specific terms that were last modified 26 August 2026, and Apache-2.0 client libraries (18). The service terms spell out caching (coordinates 30 days, place IDs exempt, a per-user geocode cache allowed) and Grounding Lite says Maps content isn't cached, stored or used to improve the model. The privacy policy is Google's general one (22). A 12-month deprecation policy and a deprecations page with dates, such as the Heatmap Layer deprecated May 2025 and gone May 2026 (20). Separate EEA terms and regional contracting entities are disclosed. A Maps Platform subprocessor list wasn't at the URL we tried (5).",
        "blend": "editorial 65, 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": "Endpoint on the vendor's domain",
        "value": "maps.googleapis.com is not on google.com",
        "points": 0,
        "max": 15
      }
    ],
    "unchecked": [
      "unchecked: whether Google Maps Platform is in scope of Google Cloud's SOC 2 and ISO 27001 reports (the compliance page returned 429)",
      "unchecked: a Maps Platform subprocessor list and data locations",
      "unchecked: MCP annotations and descriptions on the Grounding Lite tools, which are closed source",
      "unchecked: release notes for Geocoding and Grounding Lite in the last 90 days",
      "The listing's repo and packages point at the older web-services clients (Python last tagged January 2023). The current generated clients are @googlemaps/places and siblings in googleapis/google-cloud-node"
    ],
    "weaknesses": [
      "A Cloud billing account with a payment method is required before the free caps apply",
      "Coordinates may be cached for 30 days at most and only shown on a Google map",
      "No llms.txt at developers.google.com/maps",
      "Classic Geocoding and Static Maps take the key in the URL",
      "Places and Grounding Lite return reviews and AI summaries with no prompt-injection guidance"
    ],
    "agentNotes": [
      "Send X-Goog-FieldMask on every Places (New) and Routes call, since a missing mask is an error and the fields you ask for set the SKU",
      "Resolve a name with Text Search and an IDs-only field mask (free), then fetch details for the one place you need",
      "Store place IDs, refetch details, and drop cached coordinates after 30 days",
      "Retry UNKNOWN_ERROR and OVER_QUERY_LIMIT with exponential backoff, and don't retry INVALID_REQUEST",
      "Put Google Maps attribution directly after any answer grounded in Grounding Lite results"
    ],
    "requests": [
      {
        "text": "Free tier without billing",
        "reviews": 1
      },
      {
        "text": "Add a no-card free route",
        "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"
  }
}