{
  "fixes": {
    "slug": "here-location-services",
    "name": "HERE Location Services",
    "listing": "https://www.anchorterminal.com/tools/here-location-services",
    "markdown": "# Fix list: HERE Location Services\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/here-location-services, the October 2026 research run, assessed 9 October 2026. Grade C, 58 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 HERE Location Services: 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, 10 out of 100, up to 11.3 more on the total\n\nWhy it scored 10: No x402, MPP or L402 was found in the docs index or the terms (0). The Base Plan price page is public, but its table is drawn by script and showed no prices to our reader, so per-request prices score as absent. This is a limit of our reading and not a finding that prices are hidden (0 of 20). HERE's docs say a new organisation can get started for free. Whether a card is asked for was not established (10 of 20). Sign-up is a browser flow with email verification (0). Support plans are priced in public, from $50 a month for the Developer plan. Total 10.\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. Reliability, 57 out of 100, up to 8.6 more on the total\n\nWhy it scored 57: Graded on the REST APIs (Geocoding and Search v7, Routing v8) with the hosted lines. HERE's docs describe a public status page at status.here.com/status with current status, a status history tab and scheduled maintenance (20). The page is drawn by script and showed only a loading message, so the 90-day record is unread (5). No rate limit with a number was found in the docs. A Rate Limit Rules API returns an account's own rules, and the Base Plan limits sit on the unread price page (5 of 15). The Limits and Quotas page says an exceeded quota returns 429 or 503 and that a surge can be throttled for about 10 minutes, and the OpenAPI definition lists 429. No Retry-After header or backoff guidance was found, and the calls are reads (7 of 15). Monthly availability targets of 99.9 per cent are published for Geocoding and Search v7 and Routing v8, with service credits only for the Essential support plan and above (10). Both APIs are in the Active lifecycle stage (10). Total 57.\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## 3. Security \u0026 auth, 65 out of 100, up to 6.1 more on the total\n\nWhy it scored 65: Credentials are API keys, OAuth 2.0 client credentials and OAuth 2.1 `private_key_jwt` with a registered JWK, where the private key stays with the customer. Tokens are short-lived and can be scoped to a project, and an app holds two API keys or two JWKs for rotation (30). Less 10 because the documented API key method is the `apiKey` query parameter (20). The location services only read. Trusted domains limit where a key works, and app credentials do not inherit the user's permissions (15 of 20). Results carry place names from third-party sources. The Location Reasoning examples load a `guardrails://location-reasoning-usage-policy` resource and a `hlr___secure_location_reasoning` prompt, whose text was not read (7 of 15). A Usage API reports billable usage by app and project. Per-call logs were not found (6 of 15). ISO/IEC 27001:2022, 27701, 27017, 27018 and 42001 certificates, SOC 2 Type 2 scoped to Platform Foundation and Workspace, TISAX AL3 and CSA STAR Level 2 are listed. A disclosure policy of 13 July 2023 names security@here.com with a 90-day window. No bug bounty and no security.txt were found (17 of 20). Total 65.\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, 74 out of 100, up to 4.2 more on the total\n\nWhy it scored 74: `limit` sizes geocoding responses (1 to 100, default 20), and `show` and `return` parameters add optional blocks only when asked for. The MCP server lists 13 tools, two of them experimental, and passes cached route and isoline IDs between tools so geometry is not returned twice (18 of 25). Filters by country, result type, position and bounding area are documented. No offset or cursor paging was found for geocoding (15 of 20). Errors carry `status`, `title`, `code`, `cause`, `action` and `correlationId`, and the routing changelog names error codes such as `E605502` (17). Calls are reads and safe to repeat. MCP annotations were not read (14 of 20). A geocode needs only `q` and a credential. The SDKs in the docs are for maps on JavaScript, Android, iOS and Flutter, and no server-side REST client was found in the reviewed documentation (10 of 15). Total 74.\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, 60 out of 100, up to 3.5 more on the total\n\nWhy it scored 60: The newest dated API entries are Matrix Routing 8.49.0 on 9 September 2026 and Routing 8.162.0 on 7 September 2026, 30 and 32 days before the check. The Matrix entry is a documentation change, so we scored the 90-day band (20 of 30). Routing v8 had releases 8.160.0, 8.161.0 and 8.162.0 between 16 July and 7 September (20). Changelogs are public for each API, and paid support plans state response times from 72 hours down to 4. A free community channel was not checked (10 of 15). HERE SDK and Maps API for JavaScript changelogs are indexed, but their dates were not read, and no HERE entry was found in the official MCP registry (5 of 15). Package health is not visible for a closed service (5 of 10). Total 60.\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. Transparency \u0026 trust, 63 out of 100, up to 3.2 more on the total\n\nMade of editorial 52, provenance 73.\n\nWhy it scored 63: Closed service under public, dated terms. The HERE Platform Terms, effective 18 September 2023, name the contracting entity by region and govern the Base Plan (15 of 30). The terms say HERE analyses use of the platform and uses anonymised or aggregated findings to develop its products, and Essential Data Processing domains switch that off. The privacy policy of 29 August 2024 says it does not cover processing done on behalf of customers and gives no retention periods. The DPA is a PDF we did not read (14 of 30). The Product Lifecycle Policy gives six months' notice before discontinuation and 6 to 12 months for a deprecated feature, and changelogs mark deprecations with dates (20). No sub-processor list or data location was found on the pages read (3 of 20). Total 52.\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: geocode.search.hereapi.com is not on here.com (0 of 15)\n- Terms of service: read, states 7 of the 7 things a reader expects, and has 1 clause that costs points (8 of 10)\n- security.txt: not found (0 of 10)\n\n## 7. Schema \u0026 documentation, 87 out of 100, up to 2.1 more on the total\n\nWhy it scored 87: Each endpoint page has a Markdown twin holding an OpenAPI 3.0.0 definition, read for `/geocode` at version 7.157 (25). docs.here.com has a site `llms.txt` and one for each product and section (10). Endpoint descriptions state the purpose, and parameter descriptions are long, with ALPHA, BETA and RESTRICTED maturity tags. Little says when not to use an endpoint (14 of 20). Parameters are typed with 34 enums in the geocode definition, ranges such as `limit` 1 to 100 and defaults (13 of 15). 400, 405, 429 and 503 share an `ErrorResponse` schema, and the developer guide has code examples for each endpoint (12 of 15). The Routing v8 changelog is dated by entry up to 8.162.0 on 7 September 2026. The Geocoding and Search release notes are numbered by release without dates (13 of 15). The Location Reasoning tool schemas come only from `tools/list` and were not read. Total 87.\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## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- 10 July 2026. The Routing v8 changelog marks `mlDuration` as Deprecated and says `return=mlDuration` is still accepted but no longer returns a value. HERE's lifecycle policy says a deprecated feature continues to operate for 6 to 12 months after notice. Three points (https://docs.here.com/routing/docs/routing-v8-changelog.md)\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- unchecked: Base Plan prices, free monthly allowances, rate limits and whether a card is needed. https://www.here.com/get-started/pricing is drawn by script and showed only headings.\n- unchecked: the 90-day incident record. https://status.here.com/status is drawn by script, and robots.txt on that host disallows `/status`.\n- unchecked: Location Reasoning tool schemas, descriptions and annotations. They are published only through `tools/list` on https://hlr.here.ai/mcp, which we did not call. The count of 13 tools comes from the docs table.\n- unchecked: the HERE Platform Data Processing Agreement, a PDF, and with it any sub-processor list, data locations and retention periods.\n- unchecked: release dates of the HERE SDK and Maps API for JavaScript, and any GitHub repositories or server-side client libraries.\n- The Platform Terms forbid use of HERE Materials in connection with a machine learning or AI system, while HERE sells Location Reasoning for AI agents. Which terms govern Location Reasoning, and whether they lift that clause, was not established. This matters before any probe is run.\n- The acceptable use policy of 18 January 2022 lists benchmarking, scraping and data mining as prohibited. Recorded as a fact with no deduction. It matters before any probe is run.\n- The lead was right about the APIs and the MCP server. It did not say the MCP server runs on hlr.here.ai, needs an account entitlement and is also sold through AWS Marketplace.\n- The APIs answer on hereapi.com and the MCP server on here.ai, both off here.com, so `endpointOnVendorDomain` is false.\n\n## Weaknesses\n\n- Platform Terms section f forbids using HERE Materials in connection with a machine learning or AI system, generative AI included. This matters before any probe is run\n- The Base Plan price table is drawn by script, so per-request prices, free allowances and rate limits were not read\n- API keys travel in the `apiKey` query parameter\n- Results may be cached or stored outside the platform for 30 days at most, and only as HTTP caching headers allow\n- Location Reasoning returns 403 unless the account is entitled, and the docs send the reader to an account representative or AWS Marketplace\n- The acceptable use policy of January 2022 lists benchmarking and scraping among prohibited activities\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 `Authorization: Bearer` with an OAuth token where logs are kept. The `apiKey` query parameter puts the secret in every URL\n- Do not store results for more than 30 days, and follow the HTTP caching headers on each response\n- Treat 429 and 503 as throttling. HERE says a traffic surge can be throttled for about 10 minutes below the account's quota\n- Read `code`, `cause` and `action` in the error body, and quote `correlationId` to support\n- For Location Reasoning, send `initialize`, keep the `Mcp-Session-Id` header on later calls, and send a bearer token on `tools/call`\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": "C",
    "score": 58,
    "assessed": "2026-10-09",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 10,
        "maxGain": 11.3,
        "reason": "No x402, MPP or L402 was found in the docs index or the terms (0). The Base Plan price page is public, but its table is drawn by script and showed no prices to our reader, so per-request prices score as absent. This is a limit of our reading and not a finding that prices are hidden (0 of 20). HERE's docs say a new organisation can get started for free. Whether a card is asked for was not established (10 of 20). Sign-up is a browser flow with email verification (0). Support plans are priced in public, from $50 a month for the Developer plan. Total 10.",
        "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": "reliability",
        "name": "Reliability",
        "score": 57,
        "maxGain": 8.6,
        "reason": "Graded on the REST APIs (Geocoding and Search v7, Routing v8) with the hosted lines. HERE's docs describe a public status page at status.here.com/status with current status, a status history tab and scheduled maintenance (20). The page is drawn by script and showed only a loading message, so the 90-day record is unread (5). No rate limit with a number was found in the docs. A Rate Limit Rules API returns an account's own rules, and the Base Plan limits sit on the unread price page (5 of 15). The Limits and Quotas page says an exceeded quota returns 429 or 503 and that a surge can be throttled for about 10 minutes, and the OpenAPI definition lists 429. No Retry-After header or backoff guidance was found, and the calls are reads (7 of 15). Monthly availability targets of 99.9 per cent are published for Geocoding and Search v7 and Routing v8, with service credits only for the Essential support plan and above (10). Both APIs are in the Active lifecycle stage (10). Total 57.",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 65,
        "maxGain": 6.1,
        "reason": "Credentials are API keys, OAuth 2.0 client credentials and OAuth 2.1 `private_key_jwt` with a registered JWK, where the private key stays with the customer. Tokens are short-lived and can be scoped to a project, and an app holds two API keys or two JWKs for rotation (30). Less 10 because the documented API key method is the `apiKey` query parameter (20). The location services only read. Trusted domains limit where a key works, and app credentials do not inherit the user's permissions (15 of 20). Results carry place names from third-party sources. The Location Reasoning examples load a `guardrails://location-reasoning-usage-policy` resource and a `hlr___secure_location_reasoning` prompt, whose text was not read (7 of 15). A Usage API reports billable usage by app and project. Per-call logs were not found (6 of 15). ISO/IEC 27001:2022, 27701, 27017, 27018 and 42001 certificates, SOC 2 Type 2 scoped to Platform Foundation and Workspace, TISAX AL3 and CSA STAR Level 2 are listed. A disclosure policy of 13 July 2023 names security@here.com with a 90-day window. No bug bounty and no security.txt were found (17 of 20). Total 65.",
        "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": 74,
        "maxGain": 4.2,
        "reason": "`limit` sizes geocoding responses (1 to 100, default 20), and `show` and `return` parameters add optional blocks only when asked for. The MCP server lists 13 tools, two of them experimental, and passes cached route and isoline IDs between tools so geometry is not returned twice (18 of 25). Filters by country, result type, position and bounding area are documented. No offset or cursor paging was found for geocoding (15 of 20). Errors carry `status`, `title`, `code`, `cause`, `action` and `correlationId`, and the routing changelog names error codes such as `E605502` (17). Calls are reads and safe to repeat. MCP annotations were not read (14 of 20). A geocode needs only `q` and a credential. The SDKs in the docs are for maps on JavaScript, Android, iOS and Flutter, and no server-side REST client was found in the reviewed documentation (10 of 15). Total 74.",
        "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": 60,
        "maxGain": 3.5,
        "reason": "The newest dated API entries are Matrix Routing 8.49.0 on 9 September 2026 and Routing 8.162.0 on 7 September 2026, 30 and 32 days before the check. The Matrix entry is a documentation change, so we scored the 90-day band (20 of 30). Routing v8 had releases 8.160.0, 8.161.0 and 8.162.0 between 16 July and 7 September (20). Changelogs are public for each API, and paid support plans state response times from 72 hours down to 4. A free community channel was not checked (10 of 15). HERE SDK and Maps API for JavaScript changelogs are indexed, but their dates were not read, and no HERE entry was found in the official MCP registry (5 of 15). Package health is not visible for a closed service (5 of 10). Total 60.",
        "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": 63,
        "maxGain": 3.2,
        "reason": "Closed service under public, dated terms. The HERE Platform Terms, effective 18 September 2023, name the contracting entity by region and govern the Base Plan (15 of 30). The terms say HERE analyses use of the platform and uses anonymised or aggregated findings to develop its products, and Essential Data Processing domains switch that off. The privacy policy of 29 August 2024 says it does not cover processing done on behalf of customers and gives no retention periods. The DPA is a PDF we did not read (14 of 30). The Product Lifecycle Policy gives six months' notice before discontinuation and 6 to 12 months for a deprecated feature, and changelogs mark deprecations with dates (20). No sub-processor list or data location was found on the pages read (3 of 20). Total 52.",
        "blend": "editorial 52, provenance 73",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 87,
        "maxGain": 2.1,
        "reason": "Each endpoint page has a Markdown twin holding an OpenAPI 3.0.0 definition, read for `/geocode` at version 7.157 (25). docs.here.com has a site `llms.txt` and one for each product and section (10). Endpoint descriptions state the purpose, and parameter descriptions are long, with ALPHA, BETA and RESTRICTED maturity tags. Little says when not to use an endpoint (14 of 20). Parameters are typed with 34 enums in the geocode definition, ranges such as `limit` 1 to 100 and defaults (13 of 15). 400, 405, 429 and 503 share an `ErrorResponse` schema, and the developer guide has code examples for each endpoint (12 of 15). The Routing v8 changelog is dated by entry up to 8.162.0 on 7 September 2026. The Geocoding and Search release notes are numbered by release without dates (13 of 15). The Location Reasoning tool schemas come only from `tools/list` and were not read. Total 87.",
        "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"
      }
    ],
    "provenance": [
      {
        "label": "Endpoint on the vendor's domain",
        "value": "geocode.search.hereapi.com is not on here.com",
        "points": 0,
        "max": 15
      },
      {
        "label": "Terms of service",
        "value": "read, states 7 of the 7 things a reader expects, and has 1 clause that costs points",
        "points": 8,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "10 July 2026. The Routing v8 changelog marks `mlDuration` as Deprecated and says `return=mlDuration` is still accepted but no longer returns a value. HERE's lifecycle policy says a deprecated feature continues to operate for 6 to 12 months after notice. Three points (https://docs.here.com/routing/docs/routing-v8-changelog.md)"
    ],
    "unchecked": [
      "unchecked: Base Plan prices, free monthly allowances, rate limits and whether a card is needed. https://www.here.com/get-started/pricing is drawn by script and showed only headings.",
      "unchecked: the 90-day incident record. https://status.here.com/status is drawn by script, and robots.txt on that host disallows `/status`.",
      "unchecked: Location Reasoning tool schemas, descriptions and annotations. They are published only through `tools/list` on https://hlr.here.ai/mcp, which we did not call. The count of 13 tools comes from the docs table.",
      "unchecked: the HERE Platform Data Processing Agreement, a PDF, and with it any sub-processor list, data locations and retention periods.",
      "unchecked: release dates of the HERE SDK and Maps API for JavaScript, and any GitHub repositories or server-side client libraries.",
      "The Platform Terms forbid use of HERE Materials in connection with a machine learning or AI system, while HERE sells Location Reasoning for AI agents. Which terms govern Location Reasoning, and whether they lift that clause, was not established. This matters before any probe is run.",
      "The acceptable use policy of 18 January 2022 lists benchmarking, scraping and data mining as prohibited. Recorded as a fact with no deduction. It matters before any probe is run.",
      "The lead was right about the APIs and the MCP server. It did not say the MCP server runs on hlr.here.ai, needs an account entitlement and is also sold through AWS Marketplace.",
      "The APIs answer on hereapi.com and the MCP server on here.ai, both off here.com, so `endpointOnVendorDomain` is false."
    ],
    "weaknesses": [
      "Platform Terms section f forbids using HERE Materials in connection with a machine learning or AI system, generative AI included. This matters before any probe is run",
      "The Base Plan price table is drawn by script, so per-request prices, free allowances and rate limits were not read",
      "API keys travel in the `apiKey` query parameter",
      "Results may be cached or stored outside the platform for 30 days at most, and only as HTTP caching headers allow",
      "Location Reasoning returns 403 unless the account is entitled, and the docs send the reader to an account representative or AWS Marketplace",
      "The acceptable use policy of January 2022 lists benchmarking and scraping among prohibited activities"
    ],
    "agentNotes": [
      "Send `Authorization: Bearer` with an OAuth token where logs are kept. The `apiKey` query parameter puts the secret in every URL",
      "Do not store results for more than 30 days, and follow the HTTP caching headers on each response",
      "Treat 429 and 503 as throttling. HERE says a traffic surge can be throttled for about 10 minutes below the account's quota",
      "Read `code`, `cause` and `action` in the error body, and quote `correlationId` to support",
      "For Location Reasoning, send `initialize`, keep the `Mcp-Session-Id` header on later calls, and send a bearer token on `tools/call`"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-10",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}