MapQuest

# Fix list: MapQuest

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/mapquest, the October 2026 research run, assessed 8 October 2026. Grade F, 35.1 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 MapQuest: 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, 23 out of 100, up to 15.4 more on the total

Why it scored 23: Graded as a hosted service. No status page is linked from the developer site, the docs or the plans page (0). With no page there is no readable incident history (5). The reference marks endpoints 'Rate Limited Yes' and gives functional maximums (100 locations a batch, 50 a route, 25 a matrix) but no request-rate numbers (5). No 429, Retry-After or backoff guidance found (0). The Enterprise plan lists a service-level agreement, with no text published (3). The REST API is generally available and the MCP page calls the server production-ready (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.

## 2. Security & auth, 28 out of 100, up to 12.6 more on the total

Why it scored 28: REST uses API keys, several per account, created in the dashboard or by API. The MCP server uses OAuth with one scope, `mcp:tools`. That earns 20, less 10 because the `key` query parameter is the documented way to send the secret (10). No key scopes, referrer or IP restrictions, or read-only mode found in the docs (3). Place and address text is returned with no prompt-injection guidance (7). The usage endpoint reports transactions by key, service and hour (8). No security.txt, disclosure policy, bug bounty or certification found (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.

## 3. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). $0.0045 a transaction and four monthly plans are published without a login (20). 50,000 one-time free transactions, expiring 1 January 2027. The sign-up page is drawn by script, so we could not confirm that no card is needed, and half credit is given (10). A person registers in a browser. The Account API creates further keys but needs a key first (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.

## 4. Schema & documentation, 47 out of 100, up to 8.6 more on the total

Why it scored 47: `https://developer.mapquest.com/openapi.json` describes the marketing site and has an empty `paths` object, so the product APIs have no machine-readable contract. The MCP tool definitions sit behind OAuth and were not read (0). `llms.txt` indexes every API with a one-line purpose (10). The reference states each endpoint's purpose and each parameter's effect, without when-not-to-use guidance (12). Parameter tables give ranges and allowed values in prose (8). Example requests and responses on each page, and status-code pages per API (12). Versions in the path (v1, v2, v4, v5) but no 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.

## 5. Maintenance & community, 23 out of 100, up to 6.7 more on the total

Why it scored 23: The newest dated product changes are two blog announcements on 16 July 2026 (the Geolocation API and a 10,000 by 10,000 async route matrix), 84 days before the check (20). Two dated entries in 90 days. The MCP guide's version 1.2 is dated 7 July 2026, 93 days before (0). No changelog. Support is by email, untested (3). The MCP registry returns no server for 'mapquest', and the only current SDKs are browser libraries with no dated releases found (0). No package to judge (0).

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, 60 out of 100, up to 6.5 more on the total

Why it scored 60: The MCP page names 13 tools. Their definitions were not read, so context cost is scored from the count and from REST controls such as `maxResults`, `thumbMaps=false` and `outFormat` (15). Place search pages with `pageSize` 1 to 50 and filters by category, circle, bounding box or corridor (16). Status codes are documented, with geocoding and directions errors carried in the response body and problem+json on the Account API (12). Most calls read and are safe to retry. Data Manager writes have no idempotency key, and MCP annotations were not read (10). Geocoding needs only `key` and `location`. The only current SDKs are browser libraries (7).

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, 28 out of 100, up to 6.3 more on the total

Made of editorial 21, provenance 35.

Why it scored 28: Closed service. The only terms linked are System1's website terms of 26 February 2021, which allow personal, non-commercial use and do not mention the APIs. The plans page states the storage rule (5). The System1 group privacy policy of 5 July 2023 gives no retention periods and describes sale and sharing of personal information, while the plans page says 'we don't collect or sell user data' (8). No deprecation policy. Dated notices exist from 2018 only (5). The policy names categories of service providers, with no list or locations. The geocoding docs name TomTom for international queries (3).

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):

- Endpoint on the vendor's domain: www.mapquestapi.com is not on mapquest.com (0 of 15)
- Terms of service: not found (0 of 10)
- Privacy policy: not found (0 of 10)
- Status page: not found (0 of 10)
- 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 MCP tool definitions, annotations and count, which need a signed-in account (the 13 tool names come from the MCP page)
- unchecked: whether sign-up needs a card, and which terms the sign-up form shows (the page is drawn by script)
- unchecked: www.mapquest.com/.well-known/security.txt, which returned an empty 202 to our reader
- No API terms or product privacy policy were found published without a login, so `provenance.terms` and `provenance.privacy` are left out
- The MCP page mentions 'free monthly transactions' while the plans page describes 50,000 one-time credits. Which applies to MCP use was not established
- The MCP server's launch date was not found. The setup guide's version 1.2 is dated 7 July 2026
- No request-rate limit, definition of a transaction or overage price for monthly plans was found in the reviewed documentation
- The lead described a large free allowance. It is a one-time 50,000 credits that expire on 1 January 2027

## Weaknesses

- No API terms of service found. The legal link leads to System1's 2021 website terms, which allow personal, non-commercial use only
- No status page, changelog or published rate-limit numbers found
- REST keys are sent in the `key` query parameter, and no key scopes or restrictions are documented
- `openapi.json` describes the marketing site and has no paths, so the product APIs have no machine-readable contract
- Monthly plans forbid storing or caching geocodes. That needs an Enterprise account

## 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.

- Register an account and create an API key before connecting the MCP server. Every tool needs an active key, chosen by nickname on first use
- Send REST calls to `https://www.mapquestapi.com` with `key` in the query string, and redact it from logged URLs
- Read `info.statuscode` in geocoding and directions responses. 0 is success, and errors such as 610 (ambiguous location) arrive in the body
- Set `thumbMaps=false` and `maxResults` on geocoding, and `pageSize` (1 to 50) on place search, to keep responses small
- Do not store or cache geocodes on a monthly or pay-as-you-go plan

## 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.