MCP server exposing Mistral AI capabilities over MCP: chat, embeddings, FIM, vision, OCR, audio, agents, moderation, classification, files, batch
Connect Mistral MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server exposing Mistral AI capabilities over MCP: chat, embeddings, FIM, vision, OCR, audio, agents, moderation, classification, files, batch, workflows, conversations, RAG libraries, sampling, prompts, resources, and Streamable HTTP. The mistral mcp mcp server is what makes that connection.
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.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
mistral_chat — Chat completion. Supports all Mistral models, response_format, reasoning_effort for Magistralmistral_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 blockscodestral_fim — Fill-in-the-middle code completion (Codestral model)voxtral_transcribe — Audio → text. Pass diarize: true for speaker separationworkflow_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 checkpointsconnectors_list — Discover Mistral Connectors (MCP/HTTP integrations) visible to the callerconnectors_get — Fetch one connector's public metadata (never credentials)connectors_list_tools — List the MCP tools a connector exposes, with their input schemaconnectors_call_tool — Invoke a connector's tool — real MCP CallToolResult passthroughConfiguration is passed through the environment: MISTRAL_API_KEY, MCP_HTTP_HOST, MCP_HTTP_PATH, MCP_HTTP_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
This sits in the team communication group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Mistral MCP's toolset — mistral_chat, mistral_vision, mistral_ocr and 11 more — is a fair guide to whether it matches your workflow. It is maintained by swih; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Mistral MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| 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. |
| Group | Tools |
| Generation | mistral_chat_stream, mistral_embed, mistral_tool_call |
{
"mcpServers": {
"mistral": {
"command": "npx",
"args": ["-y", "mistral-mcp"],
"env": {
"MISTRAL_API_KEY": "your-value",
"MCP_HTTP_HOST": "your-value",
"MCP_HTTP_PATH": "your-value",
"MCP_HTTP_TOKEN": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| MISTRAL_API_KEY | Credential the server authenticates with. | Yes |
| MCP_HTTP_HOST | Endpoint or connection string the server talks to. | Optional |
| MCP_HTTP_PATH | Filesystem location the server is allowed to use. | Optional |
| MCP_HTTP_TOKEN | Credential the server authenticates with. | Yes |
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Inbox intelligence — search, read, draft and send Gmail through your assistant with OAuth auto-setup.
Read and write Jira, Confluence, Bitbucket, JSM and Compass from your AI client — with your own permissions.
Read and send Telegram messages through your assistant — chats, channels and history via the client API.
Enables Discord bot integration with Model Context Protocol (MCP) compatible applications like Claude Desktop.
Exposes REST APIs defined by OpenAPI specifications as Model Context Protocol (MCP) tools, facilitating seamless integration into MCP-based workflows.