# Yoofooz API Readiness Report

## API
**Name:** Mistral API
**Docs URL:** https://docs.mistral.ai/studio/agents/agents-api
**Domain:** docs.mistral.ai
**Generated At:** 2026-10-05T22:42:22.712527+00:00

## Certification
**Agent Readiness Score:** 80/100
**Certification Level:** Yoofooz Ready

## Agent Commerce Readiness
**Agent Commerce Score:** 65/100
**Agent Commerce Level:** Agent Commerce Capable

This score is separate from the core Agent Readiness Score and evaluates MCP support, scoped agent identity, machine-native payments, consumption pricing, budget controls, rate controls, deterministic errors, auditability, least-privilege security, and agent observability.

## Category Scores
- Documentation Clarity: 10
- Machine Readable Spec: 10
- Authentication Clarity: 10
- Error Handling: 10
- Rate Limit Clarity: 10
- Agent Safe Workflow Support: 5
- Sandbox Availability: 0
- Webhook Event Support: 10
- Commercial Trust: 5
- Developer Experience: 10

## Strengths
- Documentation clarity
- Machine-readable specification (OpenAPI/GraphQL/etc.)
- Authentication model clarity
- Error handling and status codes
- Rate-limit / quota behavior
- Webhook / event support
- Developer experience (SDKs, quickstart, CLI)

## Risks
- Agent-safe workflow primitives (idempotency, retries) signal is partial; clearer documentation recommended.
- Sandbox / test-mode availability signal not detected in docs.
- Commercial trust (status, SLA, compliance) signal is partial; clearer documentation recommended.

## Recommended Next Steps
- Strengthen: Document idempotency keys, test mode, dry runs, and safe retry semantics for agents.
- Provide a sandbox / test mode with test API keys for safe agent testing.
- Strengthen: Publish status page, SLA, and security/compliance posture (SOC 2, GDPR, PCI as applicable).

## Evidence Signals

### Documentation clarity
- **Source:** https://docs.mistral.ai/llms.txt
- **Matched:** getting started, quickstart, parameters, request, response, docs, guide, reference, overview
- **Evidence:** "...understand what a workspace is and create one inside your organization. getting started - [sdk clients](https://docs.mistral.ai/getting-started/clients.md): explorertabitem, - [platform..."

- **Source:** https://docs.mistral.ai/api/endpoint/beta/admin/billing
- **Matched:** getting started, request, examples, docs, reference
- **Evidence:** "...docs ⌘k vibe studio inference & models admin resources api reference search docs ⌘k toggle theme reach out try studio download openapi spec home getting started chat fim embeddings classifiers files models batch ocr audio transcriptions audio speech audio voices events realtime sessions workflows workflows..."

### Machine-readable specification (OpenAPI/GraphQL/etc.)
- **Source:** https://docs.mistral.ai/llms.txt
- **Matched:** openapi, api spec, api reference, endpoints, endpoint reference
- **Evidence:** "...html version. admin - [api reference](https://docs.mistral.ai/admin/admin-api/api-reference.md): admin api endpoint reference generated from the openapi specification. - [authentication](https://docs.mistral.ai/admin/admin-api/authentication.md): how admin api keys work, where to create them, and how..."

- **Source:** https://docs.mistral.ai/llms-full.txt
- **Matched:** openapi, api spec, api reference, endpoints, schema
- **Evidence:** "...generated admin api reference for endpoint signatures, request bodies, response schemas, and examples. the reference is generated from the latest openapi specification. | area | reference | | --- | --- | | users and invitations | [beta admin users](/api/endpoint/beta/admin/users) | | workspaces |..."

### Authentication model clarity
- **Source:** https://docs.mistral.ai/vibe/code/cli/mcp-servers.md
- **Matched:** oauth, authentication, authorization, api key
- **Evidence:** "...see [connectors](/vibe/code/cli/connectors) instead. :::info **known limitation:** the cli does not yet support mcp servers that require oauth authentication. use the `stdio` or `http` transport with an api key or other static credential. ::: supported transports | transport | use it when |..."

- **Source:** https://docs.mistral.ai/llms.txt
- **Matched:** scopes, authentication, authorization, api key, keys
- **Evidence:** "...are a public preview feature. - [google](https://docs.mistral.ai/studio/connectors/providers/google.md): how vibe by mistral ai uses google apis — scopes, data access, and privacy details for gmail, google calendar, google drive, google bigquery, and google workspace. - [direct tool calling with..."

### Error handling and status codes
- **Source:** https://docs.mistral.ai/resources/mcp.md
- **Matched:** 401, retry, troubleshooting
- **Evidence:** "...configure per-tool approval in your client to review those calls before they run. troubleshooting | problem | cause | solution | |---|---|---| | `401 ` | the key is missing, misspelled, or revoked. | export the variable in the environment that launches your client, and check the key is active in..."

- **Source:** https://docs.mistral.ai/studio/observability/evaluations/advanced-guides/retry-failed-records.md
- **Matched:** 500, retry
- **Evidence:** "...failed records and patch the results in place. why it matters a typical evaluation run can involve hundreds or thousands of llm calls. if 5 out of 500 records fail, rerunning everything wastes time and money. `retry_failed_records()` identifies which records failed (at the generation or scoring..."

### Rate-limit / quota behavior
- **Source:** https://docs.mistral.ai/studio/workflows/managing-workflows-in-production/rate_limiting.md
- **Matched:** rate limit, rate limits, quota, limits
- **Evidence:** "--- id: rate-limiting title: rate limiting sidebar_position: 1 --- # rate limiting in workflows rate limiting is a crucial aspect of workflow management that helps control resource..."

- **Source:** https://docs.mistral.ai/llms.txt
- **Matched:** rate limit, rate limits, limits
- **Evidence:** "...limits, usage, and audit logs. - [usage metrics](https://docs.mistral.ai/admin/admin-api/usage-metrics.md): retrieve billing usage, spending and rate limits, le chat activity, and vibe code analytics with the admin api. - [user provisioning](https://docs.mistral.ai/admin/admin-api/user-provisioning.md):..."

### Agent-safe workflow primitives (idempotency, retries)
- **Source:** https://docs.mistral.ai/openapi.yaml
- **Matched:** metadata, validation
- **Evidence:** "...application/json: schema: $ref: '#/components/schemas/prompt' description: getpromptversion patch: tags: - beta.prompts summary: updatepromptversionmetadata operationid: prompts_update_version_metadata parameters: - name: prompt_id in: path required: true schema: type: string title: prompt_id - name:..."

- **Source:** https://docs.mistral.ai/studio/workflows/managing-workflows-in-production/rate_limiting.md
- **Matched:** metadata
- **Evidence:** "...sdk's built-in factory for creating a properly configured mistral client inside activities. it handles authentication, telemetry, and observability metadata automatically. see [mistral client](/studio/workflows/building-workflows/mistral_client) for details. ::: **behavior**: all workflows calling..."

### Webhook / event support
- **Source:** https://docs.mistral.ai/llms.txt
- **Matched:** event types, subscriptions
- **Evidence:** "...reference](https://docs.mistral.ai/admin/monitor-comply/audit-logs/reference.md): audit log response fields, filters, actor types, target types, and event types. - [zero data retention](https://docs.mistral.ai/admin/monitor-comply/zero-data-retention.md): learn what zero data retention covers, which api..."

- **Source:** https://docs.mistral.ai/studio/agents/agents-api
- **Matched:** events
- **Evidence:** "...values to augment model abilities, such as tools, instructions, and completion parameters. conversation : a history of interactions, past events and entries with an assistant, such as messages and tool executions, conversations can be started by an agent or a model. entry : an action that can..."

### Commercial trust (status, SLA, compliance)
- **Source:** https://docs.mistral.ai/resources
- **Matched:** support, changelog, security
- **Evidence:** "...studio inference & models admin resources api reference search docs ⌘k toggle theme reach out try studio home resources build api reference sdks mcp supported languages cookbooks migration guides updates release notes changelogs security advisories knowledge base glossary error glossary known limitations..."

- **Source:** https://docs.mistral.ai/openapi.yaml
- **Matched:** support, api version
- **Evidence:** "...for text fields. $ref: '#/components/schemas/listsortdirection' - name: sort_by in: query description: 'rest-friendly alias for sort.field. supported values: created_at, last_modified_at, name, title.' schema: type: string title: sort_by description: 'rest-friendly alias for sort.field...."

### Developer experience (SDKs, quickstart, CLI)
- **Source:** https://docs.mistral.ai/llms.txt
- **Matched:** quickstart, sdk, cli, guides
- **Evidence:** "# mistral ai > developer documentation for the mistral ai platform: api references, product guides, and quickstarts for le chat, vibe, mistral ai studio, and the mistral api. every link points to the markdown version of a page (same url with a `.md` extension),..."

- **Source:** https://docs.mistral.ai/resources/mcp.md
- **Matched:** quickstart, cli
- **Evidence:** "...additional workspace access. | ask a workspace admin for the matching access, then retry. | next steps - [create a skill in studio](/getting-started/quickstarts/studio/create-skill) to give the agent something to work with. - [mcp servers in the vibe code cli](/vibe/code/cli/mcp-servers) for per-tool..."

## AI Analyst Summary
AI analysis unavailable: NVIDIA analysis failed: http 410

## Yoofooz Summary
This API has been evaluated for autonomous AI-agent usability. The score reflects documentation quality, machine-readable specification signals, authentication clarity, error handling, workflow safety, commercial trust, and developer experience.