MCP server exposing Mistral AI capabilities over MCP: chat, embeddings, FIM, vision, OCR, audio, agents, moderation, classification, files, batch
MCP server exposing Mistral AI capabilities over MCP: chat, embeddings, FIM, vision, OCR, audio, agents, moderation, classification, files, batch, workflows
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 mistral_ocr to extract text from a PDF, voxtral_transcribe to transcribe a meeting recording, or workflow_execute to start a durable multi-step process — all without leaving the agent loop.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| mistral_chat | Chat completion. Supports all Mistral models, response_format, reasoning_effort for Magistral. |
| mistral_vision | Multimodal chat with images (URL or base64). |
| mistral_ocr | Document AI — extract text, bbox, and JSON annotations from PDFs/images. Pass includeBlocks: true for OCR 4 paragraph-level blocks (text/title/table/image/equation/... with bounding boxes). |
| codestral_fim | Fill-in-the-middle code completion (Codestral model). |
| voxtral_transcribe | Audio → text. Pass diarize: true for speaker separation. |
| workflow_execute | Start a Mistral Workflow (Temporal-backed durable execution). |
| workflow_status | Poll a running workflow — returns RUNNING \ |
| workflow_interact | Signal / query a running workflow. Used for human-in-the-loop checkpoints. |
| connectors_list | Discover Mistral Connectors (MCP/HTTP integrations) visible to the caller. |
| connectors_get | Fetch one connector's public metadata (never credentials). |
| connectors_list_tools | List the MCP tools a connector exposes, with their input schema. |
| connectors_call_tool | Invoke a connector's tool — real MCP CallToolResult passthrough. |
{
"mcpServers": {
"mistral": {
"command": "npx",
"args": [
"-y",
"mistral-mcp@1.0.0"
],
"env": {
"MISTRAL_API_KEY": "YOUR_MISTRAL_API_KEY",
"MISTRAL_DEFAULT_MODEL": "ministral-3b-latest",
"MISTRAL_MCP_PROFILE": "core"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| MISTRAL_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| MISTRAL_DEFAULT_MODEL | Declared in the maintainer’s client configuration. | Check documentation |
| MISTRAL_MCP_PROFILE | Declared in the maintainer’s client configuration. | Check documentation |
Generates both vector and raster images using EverArt's AI models, providing flexible storage and format conversion.
Provides file system operations, analysis, and manipulation through a standardized tool interface.
1AIVault is a local-first desktop app that acts as a portable memory vault for AI tools. It stores your memories, decisions, preferences, and reusable skills in a local SQLite database and exposes…
A Model Context Protocol server
Expose the 5dive agent-fleet CLI as Model Context Protocol tools. Point any MCP client (Claude Desktop, Cursor, Cline, or your own) at this stdio server to file tasks, inspect and message agents, and read the fleet…
Automated DOCX Redlining Engine