# Fix list: OpenCage Geocoding API From Anchor Terminal's listing at https://www.anchorterminal.com/tools/opencage, the October 2026 research run, assessed 1 October 2026. Grade B, 69.5 out of 100. This 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. For a coding agent working on OpenCage Geocoding API: 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. ## 1. Security & auth, 47 out of 100, up to 9.3 more on the total Why it scored 47: Plain revocable keys that can be disabled or tied to IP addresses, which earns 20 with 2 back for the IP rules. Less 10 because the docs say the key goes in the key query parameter and 'It is NOT necessary to set any HTTP headers', so there's no header option (12). The API only reads, so there's nothing to approve (15). Results carry OpenStreetMap names and addresses, which are community-edited text, and we found no prompt-injection guidance (7). The MCP's get-opencage-info tool reports usage and rate state. We didn't check the dashboard's per-call visibility (3). A security policy page with a bounty programme and a SECURITY.md on GitHub. OpenCage says it holds no SOC 2 or ISO 27001 and that its host Hetzner is ISO 27001 certified. security.txt couldn't be checked because robots.txt blocks it (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-security): - 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. - 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions. - 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. - 0 to 15, audit logs or per-call visibility for the operator. - 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. ## 2. Payments & pricing, 35 out of 100, up to 8.1 more on the total Why it scored 35: No x402, MPP or L402 (0). Subscription plans are public, and one-time packs work out per request ($25 for 10,000, $175 for 100,000), so we gave most of the per-unit credit (15). A 2,500-a-day free trial with no card, for testing only (20). Signup is a browser flow (0). The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments): 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. - 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. - 20, a free tier or trial that doesn't need a card. - 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. ## 3. Schema & documentation, 77 out of 100, up to 3.7 more on the total Why it scored 77: No OpenAPI. The MCP's three tools have JSON Schema inputs, and the REST API is one endpoint described parameter by parameter (15). llms.txt with 70 or more Markdown pages, including the API reference, pricing, terms and the MCP tutorial (10). The API reference explains each parameter and when to use it, but the MCP descriptions are one line each with no when-not-to-use (12). min and max on latitude, longitude and limit, but countrycode and bounds are free strings (10). A status code table and 23 tutorials across languages (15). v1 in the path and a dated API changelog in OpenCageData/opencagedata-misc-docs, newest entry 25 June 2026 (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema): APIs and MCP servers. - 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool). - 10, llms.txt or Markdown docs served for agents. - 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. - 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs. - 0 to 15, examples and documented error responses. - 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. ## 4. Reliability, 85 out of 100, up to 3 more on the total Why it scored 85: Instatus page at status.opencagedata.com, measured by StatusCake, with forward geocoding, reverse geocoding, geosearch and the website as components (20). Every component shows 100.0 per cent over the period shown and no notices (30). Free trial limits of 2,500 a day and 1 a second, and per-second rates for each paid plan (15). 402 for a spent quota and 429 for going too fast are separate codes, and free and one-time plans get X-RateLimit-Limit, -Remaining and -Reset. There's no backoff guidance beyond '408 means try again' (10). No SLA found (0). GA (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability): Hosted APIs, MCP servers, models and platforms. - 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own). - 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. - 15, rate limits documented with numbers. - 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved. - 10, an SLA published for any paid tier. - 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. - 25, a public CI and test suite, passing on the default branch. - 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered). - 15, semver discipline and breaking changes called out in a changelog. - 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. ## 5. Maintenance & community, 66 out of 100, up to 3 more on the total Why it scored 66: The newest API changelog entry is 25 June 2026 (roadinfo speed fields), 98 days old, but the blog announced spreadsheet upload improvements on 14 August 2026, inside 90 days (20). Blog posts on 15 July, 14 August, 26 August and 5 September, but no API changelog entries in the last 90 days (10). Dependabot pull requests on the MCP repo are merged within days. We couldn't see issue reply times from git (15). In the official MCP registry as io.github.OpenCageData/opencage-geocoding-mcp, and the Python SDK released 3.4.0 on 8 June 2026 (15). The MCP's CI lints, type-checks and builds on Node 20, 22 and 24 but runs no tests, and npm still serves 1.0.3 from 11 September 2025 while the repo is at 1.0.5 (6). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 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. - 20, at least three releases or dated changelog entries in the last 90 days. - 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. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## 6. Agent ergonomics, 86 out of 100, up to 2.3 more on the total Why it scored 86: Three compact MCP tools, and the API sizes its output with limit, no_annotations, abbrv and address_only (25). countrycode, bounds, proximity and min_confidence narrow results. No pagination, which a geocoder rarely needs (18). Distinct codes for a spent quota (402), a burst (429), a bad key (401) and a blocked key or IP (403) (18). Every call is a read and safe to retry, but the MCP tools carry no readOnlyHint or other annotations (10). One required parameter, sensible defaults, and official Python (3.4.0) and JavaScript clients (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics): - 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). - 20, pagination, filtering and output-size controls. - 20, actionable, documented error responses, codes and messages an agent can recover from. - 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations. - 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. ## 7. Transparency & trust, 87 out of 100, up to 1.1 more on the total Made of editorial 84, provenance 90. Why it scored 87: Closed service with clear terms, an MIT MCP server and open-source SDKs (20). Results may be stored permanently, even after cancelling. Query logs are deleted after six months and never used to train AI, no_record turns query logging off, and the DPA is public on GitHub. The GDPR page was updated 22 July 2026 with its change history (30). A dated API changelog that announces deprecations, such as the jsonp parameter on 11 May 2026, which keeps working for existing customers. No written deprecation policy (14). Seven subprocessors with locations, and hosting at Hetzner in Germany and Finland with backups in Switzerland (20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency): - 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. - 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors). - 0 to 20, a deprecation policy or notices with dates. - 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. Provenance checks not met in full (half of this category, computed from checked facts): - security.txt: could not be fetched (0 of 10) ## What we couldn't check What 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. - unchecked: security.txt (robots.txt blocks our fetch) - unchecked: per-call usage visibility in the account dashboard - The Markdown pricing page read as 'Contact' for the Large plan, while the 30 September check recorded $1,000 a month. We left pricingNotes unchanged - No SLA found for any plan ## Weaknesses - Geocoding only, no place search or routing - The key can only be sent as a query parameter - The free trial isn't for production use - MCP server is stdio-only, has no tool annotations, and npm still serves 1.0.3 from September 2025 - No SOC 2 or ISO 27001 of its own ## What costs an agent a turn today The notes we give agents before they call it. Each one is a workaround an agent shouldn't need. - Add no_annotations=1 and limit=1 when you only need coordinates - Stop on 402, which means the day's quota is gone, and back off on 429 - Add no_record=1 when the query holds personal data - Redact the key parameter before logging request URLs - Credit OpenStreetMap wherever you show results ## What the review panel asked for - Document checkout requirements - Reconcile the Large plan price ## When it's done Send 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.