Mistralmistral.ai
Mistral's agent discovery presence is a genuine strength — partners and their agents can find the APIs without friction. However, the program has two critical gaps that will slow or block partner adoption: the developer experience is hampered by incomplete descriptions and the absence of a self-service portal, while agent usability is undermined by missing runnable collections, test scripts, and undocumented idempotency behavior.
API DesignA clean, typed, well-governed API contract agents can reason about2 pass0 warn1 fail75B
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Schema coverage & depthvia sdk | 25/25 | 1/1 (100%) public params are fully typed (no any/**kwargs). Analyzer confirms all methods have a derivable input schema. Investigated: sdk 100%. | Typed, complete request/response schemas are what make agent function-calling possible. |
| pass | Example coveragevia docs | 10/10 | Code samples in 3 language(s) across docs (top: curl, python, typescript); 7/20 pages have ≥ 2 languages on the same page. Investigated: docs 100%, sdk 100%. | Examples carry shape semantics schemas under-specify — for humans and agents alike. |
| fail | Security & governance hygienevia wellknown | 0/15 | No security.txt at /.well-known/security.txt or /security.txt. Investigated: wellknown 0%. | No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel. |
| na | Machine-readable, versioned contract | —/25 | No surface produced evidence for this capability in this run. | A current OpenAPI version with a declared versioning scheme lets agents reason about the contract. |
| na | Auth declared & discoverable | —/25 | No surface produced evidence for this capability in this run. | Agents can only authenticate when auth is declared, scoped, and discoverable. |
Developer ExperienceThe context both developers and agents need to integrate fast — onboarding, code samples, complete descriptions and worked examples2 pass1 warn2 fail57D
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Code samples in docsvia docs | 18/18 | Code samples in 3 language(s) across docs (top: curl, python, typescript); 7/20 pages have ≥ 2 languages on the same page. Investigated: docs 100%. | Multi-language samples shorten time-to-first-call. |
| pass | Changelog publishedvia sdk | 13/13 | Newest official SDK activity 0 day(s) ago. Investigated: sdk 100%. | A published changelog lets partners track changes without surprise. |
| warn | Quickstart presentvia docs | 12.5/25 | Quickstart page reachable (1 variants scanned starting at https://docs.mistral.ai/) but no runnable code sample detected in HTML or .md variant. Investigated: docs 50%. | A quickstart is the fastest path from landing page to first successful call. |
| fail | Self-service developer portalvia docs | 0/29 | No signup page detected across conventional paths (/signup, /sign-up, /register, /get-started, /console/signup, /dashboard/signup, /try, /try-free, /free, /free-trial, /start, /start-free). Investigated: docs 0%. | Self-serve key/account creation is the fast first call for partners, with no sales gate. |
| fail | Description completenessvia sdk | 0/15 | 4/4 operations lack a description. Investigated: sdk 0%. | Complete descriptions are the context humans and agents need to use endpoints. |
Agent DiscoveryPartners and their agents can find your APIs — llms.txt, registries, crawlable and reachable docs1 pass3 warn0 fail83A
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Registry & SDK presencevia docs | 28/28 | Indexed on Context7 (ericlbuehler/mistral.rs, 1499 snippets). Investigated: docs 100%, sdk 100%, cli 100%. | Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look. |
| warn | Docs reachable, not hard auth-gatedvia docs | 22.5/30 | Server ignores Accept: text/markdown header (0/50 sampled pages return markdown). Investigated: docs 75%. | Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics. |
| warn | llms.txt present, valid & comprehensivevia docs | 20.6/30 | Could not test any pages; 50 failed to fetch. Investigated: docs 69%, sdk 0%. | A valid, comprehensive llms.txt is the machine-readable entry point for agents. |
| warn | Crawlable / AEOvia wellknown | 9/12 | Sitemap present (878 entries) but carries no lastmod values. Investigated: wellknown 75%. | Bots allowed plus a fresh sitemap make docs findable by agent crawlers. |
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs0 pass3 warn2 fail57D
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| warn | Agent-navigable, token-efficient docsvia docs | 17.9/22 | No sampled pages support .md URLs (0/50 tested). Investigated: docs 81%. | Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly. |
| warn | Machine-readable errors (RFC 9457)via sdk | 14/28 | Single base error "null" present, but only 1 subclass found; a richer hierarchy lets consumers catch narrowly. Investigated: sdk 50%. | RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens. |
| warn | Description consistency across surfaces | 0.8/7 | Mean pairwise description similarity across 2 surfaces (docs, sdk) is 4% (threshold 35% for full credit). | Every surface tells the same story about what the product is. |
| fail | Agent instructions file (AGENTS.md)via wellknown | 0/10 | No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%. | An AGENTS.md gives coding agents explicit setup, auth, and usage instructions to interpret and operate the API — beyond llms.txt's link index. |
| fail | Docs structured datavia docs | 0/8 | Neither JSON-LD nor OpenGraph/meta tags detected across 3 assessed pages (3 JS-rendered). Investigated: docs 0%. | Structured data (JSON-LD/schema.org) on docs pages gives agents an unambiguous parse target and is what answer engines cite. Detected on the JS-rendered head (Firecrawl) for a bounded page budget, so JS-injected JSON-LD is now caught; pages we can't render are excluded rather than failed. |
| na | Operation purpose clarity | —/25 | No surface produced evidence for this capability in this run. | Agents select the right endpoint from its summary + operationId; clear, named operations make tool-selection reliable — the strongest driver of correct tool choice. |
Agent UsabilityAgents have the context to use your APIs reliably, not just find them0 pass1 warn2 fail45F
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| warn | Sandbox separationvia sdk | 10/20 | No test-mode flag or sandbox environment is exposed. Investigated: sdk 50%. | An isolated environment lets agents exercise destructive operations safely. |
| fail | Idempotency documentedvia sdk | 0/27 | No built-in retry machinery was found; transient failures are not retried. Investigated: sdk 0%. | Documented idempotency lets agents retry safely. |
| fail | Runnable collection with test scriptsvia platform | 0/9 | No public Postman workspace discovered for the org. Investigated: platform 0%. | A public, maintained collection with assertions is runnable truth agents validate against. |
| na | Rate-limit signaling | —/22 | No surface produced evidence for this capability in this run. | Machine-readable rate-limit headers let agents throttle adaptively. |
| na | Pagination documented & consistent | —/22 | No surface produced evidence for this capability in this run. | Consistent, documented pagination lets agents traverse collections. |
Resources Discovered
The public resources we found for Mistral — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.
| Agent hints | Context7 (1,499) |
|---|