TomTom Maps APIs + MCP by TomTom

# Fix list: TomTom Maps APIs + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/tomtom, the October 2026 research run, assessed 1 October 2026. Grade C, 55.1 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 TomTom Maps APIs + 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. Reliability, 30 out of 100, up to 14 more on the total

Why it scored 30: A ServiceNow status page with per-API status (service available, planned maintenance, P1 and P2 incidents), but by TomTom's own description it keeps only the last five days, so we gave 15 of 20. With no 90-day history to read, the record scores 5. TomTom's REST docs render client-side and two Markdown paths we tried returned 404, so we found no published QPS limits or 429 guidance. That's a gap in what we could read, not proof they're missing (0). The MCP maps a 429 to a typed BusyError with a message, and we found nothing on Retry-After (5). No SLA found (0). Orbis APIs went GA on 8 July 2026, but the hosted MCP is in public preview and the README says some Orbis and EV services may not be enabled on every account (5).

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.

## 2. Payments & pricing, 25 out of 100, up to 9.4 more on the total

Why it scored 25: No x402, MPP or L402 (0). Free allowances are public, but the pricing page re-read on 2 October shows no paid rate as a number, only an estimator in euros our reader couldn't run and a contact-sales link, so we gave 5 of 20. A no-card free allowance of 20,000 geocodes, 20,000 reverse geocodes and 20,000 routes a month, with Search and Matrix at 2,500 (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. Security & auth, 51 out of 100, up to 8.6 more on the total

Why it scored 51: API keys from the developer portal, limited to the products selected for them, which earns 25. Less 10 because REST calls take the key as the key query parameter. The hosted MCP takes a tomtom-api-key header, and its source carries OAuth protected-resource metadata and a token exchange that the README doesn't document (15). Keys can be limited by product and every tool reads (16). Results include POI names and traffic incident text with no prompt-injection guidance. An app-only tool, tomtom-get-api-key, returns the raw key as text to the map app and relies on the client honouring visibility ['app'] to keep it from the model (6). We didn't find per-call logs or usage reporting we could read (0). HackerOne disclosure programme with a 3 business day first response, Veracode scanning in CI with a public triage file dated 14 September 2026, and no security.txt per the 30 September check (14).

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.

## 4. Schema & documentation, 71 out of 100, up to 4.7 more on the total

Why it scored 71: No public OpenAPI that we found. The MCP's tools have Zod schemas with 223 described fields (22). docs.tomtom.com/llms.txt indexes about 180 pages, many as .md, including the MCP overview (10). Tool descriptions are mostly one line, such as 'Convert street addresses to coordinates.', with little on when not to use a tool (12). Typed fields with constraints, few enums (11). We couldn't read the REST error reference. The MCP returns typed errors per status code (8). Versioned REST paths, but the MCP CHANGELOG.md jumps from 1.1.0 (18 September 2025) to Unreleased while tags run to v1.6.10 (8).

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.

## 5. Agent ergonomics, 78 out of 100, up to 3.6 more on the total

Why it scored 78: 15 model-visible tools on the Orbis backend plus three app-only helpers, with no toolsets or filtering (15). limit, countries, boundingBox, poiCategories, and a fields parameter on traffic that the unreleased fixes make work (16). Typed MCP errors for 400, 403 and 429 with messages, and a README section on 403 'missing permissions' (15). All 18 tools carry readOnlyHint true, destructiveHint false and idempotentHint true (20). Official map SDKs for web, Android and iOS but no Python client we found. show_ui defaults to true, which needs an MCP Apps client to render (12).

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.

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

Made of editorial 41, provenance 80.

Why it scored 61: Closed APIs with an Apache-2.0 MCP server. The terms page renders client-side and returned no text on 30 September, 1 October or 2 October, and developer.tomtom.com/legal redirects to it, so we can't call the terms clear or unclear (10). The privacy policy names TomTom International BV and was last edited 1 August 2024. Its more-information page gives retention for account data (lifetime of the account), support records (30 days for non-account holders) and tax records (7 years), but nothing for location data, IP addresses or API requests, and storage and caching rules for API results are unverified (11 of 30). llms.txt links a deprecation policy page, but it renders client-side, its .md twin returns 404, and its notice period is unverified. The Orbis GA notice says the older APIs stay until Orbis reaches parity, with no date (8). The privacy pages name subprocessors with purposes (AWS EMEA, Microsoft Ireland, Grafana, Zendesk, Airship, Jira and Confluence, TomTom affiliates and generative AI model providers) and say data is stored by default in "certain European countries" and where providers sit, without saying which apply to API traffic (12 of 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):

- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 86 out of 100, up to 1.2 more on the total

Why it scored 86: MCP v1.6.10 on 23 September 2026 (30). Five tags in the last 90 days, v1.6.6 (14 July) to v1.6.10 (23 September) (20). Pull requests from several maintainers merged up to 1 October 2026. We couldn't see issue reply times from git (18). The npm package is current at 1.6.10, but the server isn't in the official MCP registry per the 30 September check (8). CI runs type checks, lint, build, a Playwright end-to-end test and a Veracode scan, with dependabot (10).

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.

## 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: terms of service, including caching and storage rules. The page renders client-side on every attempt from 30 September to 2 October, and developer.tomtom.com/legal redirects to it.
- unchecked: QPS limits, 429 handling and the REST error reference. docs.tomtom.com/llms.txt indexes the Navigation SDK, not the REST APIs, and the REST pages render client-side.
- unchecked: deprecation policy notice period. The page renders client-side and its .md twin returns 404.
- unchecked: per-1,000 paid rates, which sit behind a euro estimator. The pricing page shows no paid rate as a number.
- Which of the subprocessors and storage locations on TomTom's general privacy pages apply to API traffic, and how long API request and location data is kept.
- When the Genesis removal on main ships, the listing's authNotes, agent notes and connect config that mention the backend header will need another pass. v1.6.10 of 23 September is still the latest tag on 2 October.

## Weaknesses

- Terms, rate limits and deprecation policy render client-side, so storage rules and notice periods are unverified
- Status page keeps only five days of history
- Paid prices only through a euro estimator
- Hosted MCP in public preview and missing from the MCP registry
- Only 2,500 free Search and Matrix calls a month

## 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.

- Use tomtom-geocode (20,000 free) rather than tomtom-fuzzy-search (2,500 free) when you have a full address
- Don't send tomtom-maps-backend in new configs, since the next release stops reading it and Orbis is already the hosted default
- Read a 403 'missing permissions' as the key lacking Orbis or EV products, and enable them in the developer portal
- Pass show_ui false when the client can't render MCP Apps, or you'll get a JSON summary instead of a map
- Redact the key parameter before logging REST URLs

## What the review panel asked for

- Document needed key products
- Publish per-1,000 rates
- Document MCP billing

## 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.