# Fix list: Azure Maps

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/azure-maps, the October 2026 research run, assessed 8 October 2026. Grade B, 67.9 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 Azure 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. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Per-1,000-transaction prices are public without a login through the Azure Retail Prices API, $4.50 on each Gen2 meter. The pricing page showed our reader the free amounts but no dollar figures (20). Free monthly transactions exist, 5,000 for search and 1,000 for routing, but an Azure account asks for a card to verify identity (0). A person signs up in a browser and creates the Maps account (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.

## 2. Security & auth, 66 out of 100, up to 6 more on the total

Why it scored 66: Microsoft Entra ID OAuth tokens with Azure roles, SAS tokens limited to 24 hours with a rate cap and allowed regions, and two subscription keys that can be regenerated in turn (30). Less 10 because the authentication guide tells callers to add the subscription key as a URL parameter, and Search 1.0 declares the key as a query parameter (20). Built-in reader roles, custom roles down to one service such as `Microsoft.Maps/accounts/services/search/read`, and `disableLocalAuth` to turn keys off. The data-plane APIs only read. A subscription key reaches every API on the account (18 of 20). Place names, addresses and traffic incident text come from third parties, and no prompt-injection guidance was found (5 of 15). Azure Monitor metrics show usage, errors and availability for 93 days. Per-request logs were not found in the Azure Maps docs (6 of 15). MSRC coordinated disclosure and bounty policies, and Azure Maps is on the FedRAMP High audit scope list dated 21 September 2026. The microsoft.com security.txt passed its Expires date on 23 September 2026, and we did not confirm Maps on a SOC 2 scope list (17 of 20).

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. Agent ergonomics, 73 out of 100, up to 4.4 more on the total

Why it scored 73: API reading of the checklist. Geocoding returns five results by default and `top` caps them at 20, but there is no field selection and each response is a full GeoJSON collection (18 of 25). `bbox`, `countryRegion`, `coordinates` and `resultTypes` filters, and Search 1.0 adds `limit`, `ofs`, `categorySet` and `brandSet` (17 of 20). Errors follow the Azure shape with `code`, `message`, `target` and `details`, and batch responses carry an error per item. No list of codes was found (13 of 20). Every data-plane call is a read, route POSTs have no side effects, and failed calls are not billed. No retry guidance for 429 was found (15 of 20). Geocoding needs only `api-version` and a query. Client libraries exist for Python, JavaScript, .NET and Java, all beta (10 of 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.

## 4. Reliability, 81 out of 100, up to 3.8 more on the total

Why it scored 81: Hosted reading. Azure status page with a history of post-incident reviews (20). The history lists three incidents in the last 90 days, West US network connectivity on 23 July 2026 (14:44 to 19:41 UTC), Azure OpenAI and Cognitive Services in Sweden Central on 29 September, and gateway services in several regions on 30 September. None names Azure Maps. The page lists only broad incidents, so there is no service-level history for Maps, and we count the record as minor (20 of 30). Default limits published per service, 500 requests a second for search, 250 for reverse geocoding and 50 for routing (15). The service answers 429 over the limit and doesn't bill 429, 408 or 5xx responses, and data-plane calls are reads, so a retry is safe. No Retry-After header or backoff guidance was found in the reviewed documentation (6 of 15). The SLA for Online Services of 1 October 2026 commits to 99.9 per cent per API, with 10 and 25 per cent credits (10). Search 2026-01-01 and Route 2025-01-01 are stable versions. The REST index still labels autocomplete a preview (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, 67 out of 100, up to 2.9 more on the total

Why it scored 67: Read as a closed service with official SDKs. The spec repository's newest Maps commits are from 30 September 2026, removing Render 1.0 after its retirement on 17 September and clarifying autocomplete result types (30). Seven dated Maps commits since 28 July 2026, plus the Gen1 pricing retirement on 15 September. Most are description changes and retirements, not new operations (20). No API changelog. Microsoft Q&A and a feedback forum are linked from each docs page, which we did not read (8 of 15). The REST client libraries are all beta and lag the service, `azure-maps-search` 2.0.0b2 on PyPI from 12 December 2024 and `@azure-rest/maps-search` 2.0.0-beta.4 on npm from 22 August 2025, with npm's `latest` tag still on beta.3 (5 of 15). The libraries live in the azure-sdk monorepos, CI not checked (4 of 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.

## 6. Schema & documentation, 83 out of 100, up to 2.8 more on the total

Why it scored 83: OpenAPI 2.0 documents for each service are public in `Azure/azure-rest-api-specs`, generated from TypeSpec since April 2026 (25). learn.microsoft.com returns each page as Markdown when `?accept=text/markdown` is added, though `llms.txt` returns 404 (10). Operation descriptions state purpose, and the geocoding and migration pages say when to use geocoding, autocomplete or batch and when not to (16 of 20). Typed parameters with ranges such as `top` from 1 to 20, 18 enums in the Search document and 48 in Route, and required fields marked (13 of 15). Examples on all 16 Search and Route operations, but errors are one default response with an `x-ms-error-code` header and no list of codes found (10 of 15). Dated `api-version` values and migration guides for Search, Route, Render and Traffic 1.0, but no API changelog page. The release notes cover the Web SDK only (9 of 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.

## 7. Transparency & trust, 74 out of 100, up to 2.3 more on the total

Made of editorial 69, provenance 78.

Why it scored 74: Closed service under Microsoft's Product Terms, which carry a section of Azure Maps rules on storage, navigation and attribution, with MIT client libraries (15 of 30). The docs say requests and input data are stored only in the chosen geography and that queries go to TomTom without a link to the customer. No retention period for request data was found, and we did not read the Data Protection Addendum (22 of 30). The Modern Lifecycle Policy promises 12 months' notice before support ends. Gen1 pricing and Render 1.0 retired on stated dates in September 2026, while Search 1.0 is superseded with no date (16 of 20). TomTom is named as a subprocessor, and European and United States endpoints fix the data location. The full sub-processor list sits on the Service Trust Portal, which we did not read (16 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):

- Terms of service: read, states 4 of the 7 things a reader expects, and has 1 clause that costs points (5.4 of 10)
- Privacy policy: read, states 8 of the 8 things a reader expects, and has 1 clause that costs points (8 of 10)
- Changelog: not found (0 of 10)
- security.txt: published but past its Expires date (5 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 Azure updates feed for Azure Maps, which the docs link in place of an API changelog. We did not open it.
- unchecked: the Microsoft Products and Services Data Protection Addendum and the sub-processor list on the Service Trust Portal.
- unchecked: whether Azure Maps is on a current SOC 2 or ISO 27001 scope list. Only the FedRAMP audit scope page was read.
- unchecked: GitHub issue response times for the Maps client libraries, and their CI.
- The pricing page showed our reader no dollar figures, so unit prices come from the Azure Retail Prices API, which lists one $4.50 tier and no volume steps.
- When Search 1.0 retires, and whether place search will move to a newer version. The migration guide gives no date.
- `lastRelease` is the date of the newest Maps commit in the spec repository (30 September 2026), since no API changelog exists.
- The lead was right on the facts checked, with one gap. The current Search version has no place search.

## Weaknesses

- Place and category search exist only in Search 1.0. Search 2026-01-01, which supersedes it, has geocoding, autocomplete, reverse geocoding and polygons
- Every REST client library is a beta. `azure-maps-search` on PyPI was last released on 12 December 2024
- The authentication guide tells callers to put the subscription key in the URL, and the key reaches every REST API on the account
- An Azure account needs a card and a browser signup before the free monthly transactions apply
- No Retry-After header or backoff guidance for 429 was found in the reviewed documentation, and no API changelog page

## 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 in the `subscription-key` header, or use `Authorization: Bearer` with `x-ms-client-id`. The key also works as a URL parameter, which leaks into logs.
- Call `GET /geocode?api-version=2026-01-01` for addresses. It can return 200 with no results, so check `confidence`, `matchCodes` and the entity type before use.
- Use Search 1.0 (`/search/poi/json`, `/search/nearby/json`, `/search/fuzzy/json`) for places. The 2026-01-01 version has no place search.
- Use `eu.atlas.microsoft.com` or `us.atlas.microsoft.com` to keep request data in that geography.
- Don't store route or tile results beyond six months, and never for serving several users. The product terms allow keeping geocodes while the account is active.

## 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.