Stadia Maps by Stadia Maps

# Fix list: Stadia Maps

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/stadia-maps, the October 2026 research run, assessed 1 October 2026. Grade B, 65.5 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 Stadia Maps: 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, 40 out of 100, up to 10.5 more on the total

Why it scored 40: Revocable keys per property with rotation through the Account Management API and a header option (`Authorization: Stadia-Auth`), which earns 25. Less 10 because api_key in the query string is a documented option and the OpenAPI spec defines only that one (15). The APIs only read, but keys aren't scoped to particular APIs (12). Results carry OpenStreetMap names, websites and opening hours, which are community-edited text, and we found no prompt-injection guidance (7). Dashboard usage and billing threshold alerts added on 20 August 2026 (6). 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, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Credit costs per call and per-1,000-credit overage published without login (20). Free tier of 200,000 credits a month and a 14-day Professional trial, both with no payment method, though the free tier is for development, testing and demos 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. Reliability, 63 out of 100, up to 7.4 more on the total

Why it scored 63: Instatus page with 27 components across maps, routing, geocoding and data APIs, plus RSS and Atom history back to April 2025 (20). One incident in the 90 days, a multi-service outage on 25 September 2026 that touched 23 components and lasted from 10:20 to 10:22 UTC, so minor (20). The FAQ says there's no fixed requests-a-second limit and the cap is the monthly credit pool, with credits per call published (12). A 429 is what you get when credits run out until the next cycle, with no Retry-After and no backoff guidance, so an agent can't tell a spent month from a burst (3). No SLA. The terms say the service is provided as is (0). The APIs are GA, but the MCP server has no release (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, 80 out of 100, up to 3.3 more on the total

Why it scored 80: Six MCP tools, pared down on 20 June 2025 'to save on context tokens' (25). size, layers, boundary filters and focus points on geocoding, and a bulk geocoding endpoint (18). The same 429 means a burst or a spent month, which costs a turn to work out (12). Every call reads, but the MCP tools carry no readOnlyHint or other annotations (10). Official generated SDKs in TypeScript and Python, with sensible defaults (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.

## 5. Schema & documentation, 86 out of 100, up to 2.3 more on the total

Why it scored 86: Public OpenAPI document at api.stadiamaps.com/openapi.yaml, version 11.1.0, from which the TypeScript and Python SDKs are generated (25). llms.txt at docs.stadiamaps.com, per the 30 September check (10). The MCP's six tool descriptions say when not to use a tool, for example bulk-geocode warns against POI names (14). Zod inputs with minimums such as at least two route locations, but some fields are loose strings (12). Docs examples per endpoint. We didn't read an error reference (10). A dated public changelog with 14 entries since June 2026 and a Keep a Changelog file in each SDK (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.

## 6. Maintenance & community, 80 out of 100, up to 1.8 more on the total

Why it scored 80: Changelog entry on 30 September 2026 (30). 14 dated changelog entries since 4 June 2026 (20). A public changelog and support desk, but the MCP repo's last commit is 29 July 2025 (10). Official TypeScript SDK v9.1.0 and Python SDK v8.1.0, both tagged 27 April 2026 (15). SDK CI runs integration tests against the live API, but the MCP server has no CI, no tagged release, no npm package and no registry entry (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, 79 out of 100, up to 1.8 more on the total

Made of editorial 72, provenance 86.

Why it scored 79: Closed service with clear terms, last updated 18 March 2026, a BSD-3-Clause MCP server and open-source SDKs (20). Server logs kept about 7 to 14 days, account data deleted within 30 days of closure, a DPA, and per-plan storage rules spelt out. The privacy policy was updated 1 October 2026 (28). No deprecation policy. The terms promise 30 days' notice for fee increases and reasonable efforts for other material changes (6). Third-party processors listed with locations in the privacy policy, and hosting described as primarily US (18).

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: stadiamaps.com, registered 2016-11-30 (9 years) (11 of 15)
- 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: a security or vulnerability disclosure page and any certifications
- unchecked: an error reference beyond 429, and whether 429 for spent credits carries a different body from a rate limit
- Whether the MCP server is still maintained, given no commits since 29 July 2025
- The benchmarking clause in the terms may restrict our own probes and task suite in this category

## Weaknesses

- Free plan is for development, testing and demos only
- The same 429 signals a burst or a spent month of credits, with no Retry-After
- No SLA, no security.txt and no disclosure policy found
- MCP server has no release, no CI and no commits since 29 July 2025
- The terms forbid benchmarking against competitors without written permission

## 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 `Authorization: Stadia-Auth <key>` rather than in the URL
- Try Autocomplete v2 (1 credit) before a full geocode (20 credits) when a name is enough
- Check the dashboard's credit balance before retrying a 429, since it may mean the month is spent
- Don't write geocodes to a database on Free or Starter
- Use bulk-geocode for addresses only, not POI names

## What the review panel asked for

- Ship a hosted MCP
- Separate burst and quota 429s

## 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.