Geoapify Location Platform + MCP by Geoapify

# Fix list: Geoapify Location Platform + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/geoapify, the October 2026 research run, assessed 1 October 2026. Grade C, 55.5 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 Geoapify Location Platform + 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.

## 1. Security & auth, 29 out of 100, up to 12.4 more on the total

Why it scored 29: Plain API keys per project, which earns 20. Less 10 because the specs call the apiKey query parameter 'Recommended authentication method for public APIs'. The x-api-key header works too and the spec warns that keys in URLs can be logged (10). The APIs only read (12). Results are OpenStreetMap names and addresses, community-edited text, with no prompt-injection guidance (7). We didn't find per-call logs we could read (0). No security.txt per the 30 September check, and we found no disclosure policy, bug bounty or certification (0).

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, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Public plan prices with credit costs per request (1 credit for a simple geocode, place search or route), but no per-unit overage price, since limits are soft and Geoapify asks heavy users to upgrade (10). Free plan of 3,000 credits a day with no card, and commercial use allowed with attribution (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. Reliability, 60 out of 100, up to 8 more on the total

Why it scored 60: status.geoapify.com redirects to an UptimeRobot page, which the 30 September check missed. Its data didn't load for our reader, so we gave 15 of 20 for the page and 5 for a history we couldn't read. Per-plan rates published, 5 requests a second on Free up to 30 on API 250 (15). 429 is in the OpenAPI specs as 'Rate limit or quota exceeded' with a JSON body, but there's no Retry-After or backoff guidance, and limits are soft on paid plans (7). 99.5 per cent monthly availability on every paid plan with 10 or 50 per cent discounts below it (10). The APIs are GA. The MCP page gives no launch stage or date (8).

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.

## 4. Agent ergonomics, 72 out of 100, up to 4.6 more on the total

Why it scored 72: 11 MCP tools, which puts it just into the 11 to 30 band (15), with 3 back because each tool has its own OpenAPI spec so an integration can import one tool without the full catalogue (18). limit, type, filter, bias, lang and format on geocoding (18). Errors come as JSON with statusCode, error and a readable message (16). Every call reads and the four geometry tools run without an API call, but the docs don't mention MCP annotations (10). One required parameter on most calls. Official JavaScript autocomplete and route planner SDKs, no Python client we found (10).

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.

## 5. Schema & documentation, 74 out of 100, up to 4.2 more on the total

Why it scored 74: OpenAPI 3.1 specs for 22 APIs and a separate spec per MCP tool in geoapify/geoapify-openapi-specs, with documented 400, 401, 429 and 500 responses (25). apidocs.geoapify.com/llms.txt serves the HTML home page, and we found no Markdown docs for agents (0). MCP tool descriptions say what a tool doesn't do and which tool to use instead, for example calculate_route_matrix sends you to calculate_route for geometry (18). Typed parameters with limits such as limit at most 100, and enums for type and format (13). Error examples in the specs, such as '"limit" must be less than or equal to 100', and a playground per API (13). v1 paths and versioned specs (forward geocoding 1.1.1), but no public changelog (5).

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.

## 6. Maintenance & community, 61 out of 100, up to 3.4 more on the total

Why it scored 61: The OpenAPI repo added Places POST and Routing geometry details on 25 September 2026, six days before this check (30). Spec commits on 1, 2 and 25 September and an autocomplete SDK release (v3.1.0) on 27 July, but no changelog (15). No public changelog, and we didn't test support response (5). The JavaScript SDKs are current. The official MCP isn't in the MCP registry, per the 30 September check (6). The autocomplete SDK carries Jest tests (5).

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.

## 7. Transparency & trust, 64 out of 100, up to 3.2 more on the total

Made of editorial 52, provenance 76.

Why it scored 64: Closed service with readable terms, version 5 of 2 February 2024, under Cypriot law (15). The privacy policy, updated 1 April 2026, says data for successful requests is held no longer than 24 hours and that hosting is in EU data centres, with custom DPAs on request (possibly at a cost). The docs say Places and Batch results can be cached or stored with no limits, while the terms say nothing on storage (22). No deprecation policy, and the terms reserve the right to change or end the service without notice (0). Six processors named, including Hetzner (Germany), Cloudflare and Google Firebase, without locations for most (15).

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):

- Domain age: geoapify.com, registered 2018-10-26 (7 years) (11 of 15)
- Changelog: not found (0 of 10)
- security.txt: not found (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: the status page's uptime figures and incident history (the UptimeRobot page didn't load its data)
- unchecked: whether keys can be restricted by origin or IP, and per-call usage visibility in the dashboard
- unchecked: MCP tool annotations on the hosted server
- Whether 'Cache/store results with no limits' in the docs covers forward and reverse geocoding, since it appears beside Places and Batch

## Weaknesses

- No security.txt, disclosure policy, bug bounty or certification found
- No public changelog or deprecation policy, and the terms allow changes without notice
- Storage rights appear in the docs but not in the terms
- The specs recommend the apiKey query parameter for public APIs
- Credits are counted per day, so bursts hit the cap early

## 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.

- Send the key as x-api-key, which the specs support, rather than apiKey in the URL
- Use api-eu.geoapify.com when the data has to stay on EU infrastructure
- Use calculate_route for geometry and directions, and calculate_route_matrix only for travel times between many points
- Read a 429 'Quota exceeded' as the day's credits being gone, not a burst, and wait for the daily reset
- Show OpenStreetMap attribution wherever you display results

## What the review panel asked for

- Add programmatic signup
- Publish credit cost per operation
- State overage terms

## 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.