Mmcp.market

Mistral MCP server

by Swih·io.github.Swih/mistral-mcp·v0.8.2·15 stars
No reviews yet

Mistral AI MCP server: chat, OCR, Voxtral audio, Codestral FIM, vision, agents, batch.

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

15 stars106 downloads/wk

Reviews

Write one

Nobody has reviewed Mistral yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Mistral tools (26, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • batch_cancelwrite action

    Request cancellation of a running batch job. Completed requests still count for billing.

  • batch_createwrite action
  • batch_get

    Fetch a batch job's current status and counters.

  • batch_list

    List batch jobs with optional filters.

  • codestral_fim
  • files_deletewrite action

    Delete a file by id. This is irreversible.

  • files_get

    Retrieve a single file's metadata by id.

  • files_list

    List files owned by this API key, with optional filters.

  • files_signed_url

    Generate a short-lived, signed URL to download a file.

  • files_uploadwrite action
  • mcp_sample
  • mistral_agent
  • mistral_chat
  • mistral_chat_stream
  • mistral_classify
  • mistral_embed
  • mistral_moderate
  • mistral_ocr
  • mistral_tool_call
  • mistral_vision
  • process_document
  • voxtral_speak
  • voxtral_transcribe
  • workflow_executewrite action
  • workflow_interact
  • workflow_status

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan35 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

Install Mistral in Claude Code, Cursor or VS Code

Runs npx -y mistral-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mistral-mcp -- npx -y mistral-mcp
Add to Cursor

What the publisher says

From the Mistral repository's README, as published. We do not edit it. Read it on GitHub

mistral-mcp

Mistral, wherever you run it.

MCP server for the full Mistral AI API — chat, OCR, audio (Voxtral), code (Codestral), vision, agents, batch, durable workflows — against Mistral Cloud or your own infrastructure.

Plug into Claude Code, Cursor, Zed, Windsurf, or Claude Desktop in one command.

Version française : README.fr.md

What this is

mistral-mcp exposes the full Mistral AI API as a set of MCP tools, resources, and prompts. An MCP client (Claude Code, Cursor, etc.) can call mistralocr to extract text from a PDF, voxtraltranscribe to transcribe a meeting recording, or workflow_execute to start a durable multi-step process — all without leaving the agent loop.

Unique to Mistral and not available from other MCP servers:

  • mistral_ocr — Mistral Document AI: structured text + bbox annotations from any PDF or image
  • voxtral_transcribe — Voxtral: transcription with optional speaker diarization
  • codestral_fim — Codestral fill-in-the-middle (FIM) for inline code completion
  • workflow_* (6 tools) — Temporal-backed durable execution: what is deployed and runnable, what is running, human-in-the-loop signals, and graceful or forced stop
  • French-optimized models (mistral-large-latest, mistral-medium-latest) and curated French prompts

What this server does not expose: fine-tuning, user management, non-FR/EN prompts.

Why this matters for European teams

mistral-mcp is designed for teams that want to use Mistral capabilities inside MCP clients (Claude Code, Cursor, Zed, Windsurf, Claude Desktop) while keeping control over deployment, API keys, cache behavior, and tool exposure.

This can be useful for European organisations evaluating AI stacks under GDPR, DORA, sector-specific constraints (HDS, EBA), or internal sovereignty requirements.

What this project provides:

  • self-hosted MCP server, no mandatory SaaS proxy
  • bring-your-own Mistral API key (BYOK) — Mistral states API data is not used to train its models
  • MISTRALBASEURL routes every call to your own OpenAI-compatible endpoint (vLLM, TGI, LiteLLM, an internal gateway) — no traffic to api.mistral.ai
  • lean core profile and focused metier-docs profile to limit tool exposure
  • processdocument cache configurable per-call and via MISTRALMCPCACHEDIR, with a retention window (MISTRALMCPCACHETTLHOURS, default 7 days, 0 to disable) after which entries are deleted, not merely bypassed
  • ID document cache bypass enabled by default, even when kind:"auto" resolves to id_document
  • Streamable HTTP + bearer auth path for controlled / on-prem deployments
  • French-first prompts and skills (meeting minutes, legal summary, invoice reminder, commit message, email reply)
  • Mistral Free mode includes API usage for evaluation, subject to the model-specific limits shown in the Studio Limits page

What this project does NOT claim:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Mistral: common questions

Is Mistral MCP server safe?
Mostly: it is graded B (83/100). Read the Mistral safety report
How do I install Mistral?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Mistral need an API key?
Yes. The registry entry asks for MISTRAL_API_KEY.
Is Mistral maintained?
The last commit was 6 days ago (2026-09-22). The latest release is v0.8.2.
What can I use instead of Mistral?
Servers from other publishers that do the same job: Openrouter Multimodal MCP server, FunASR MCP server and Transloadit Media Processing MCP server. Compare all Mistral alternatives.

Alternatives to Mistral

Same job from other publishers: the closest match first, then the best rated.

All Mistral alternatives →
  • Openrouter Multimodal
    Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP.
    B
  • FunASR
    Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
    A
  • Transloadit Media Processing
    Process video, audio, images, and documents with 86+ cloud media processing robots.
    A
  • NotebookLM MCP
    Automate Google NotebookLM — Q&A with citations, audio, video, content generation
    C
  • three.ws Vision
    Image understanding for AI agents — analyze and describe any image via the three.ws pipeline.
    More from nirholas →
    A

More from Swih →