Swih/mistral-mcp
by Various
Full Mistral AI MCP server — OCR, Voxtral audio, Codestral FIM, durable workflows, document extraction — for Claude Code, Cursor, Windsurf, Zed, Mistral Connectors
MCP
Swih/mistral-mcp
Added 1 June 2026
Overview
An MCP server that exposes Mistral AI capabilities including OCR, Voxtral audio, Codestral Fill-in-the-Middle, durable workflows, and document extraction. Designed to integrate with Claude Code, Cursor, Windsurf, Zed, and Mistral Connectors via the Model Context Protocol written in TypeScript.
Best for
Best for
Developers who want to integrate Mistral AI capabilities into their IDE or MCP-compatible workflow
Use cases
- Run document extraction and OCR tasks directly from an IDE or terminal
- Generate or complete code with Codestral FIM during development
- Execute durable workflows and process audio using Voxtral from supported editors
Notes
An MCP server that exposes Mistral AI capabilities including OCR, Voxtral audio, Codestral Fill-in-the-Middle, durable workflows, and document extraction. Designed to integrate with Claude Code, Cursor, Windsurf, Zed, and Mistral Connectors via the Model Context Protocol written in TypeScript.
6 stars on GitHub. Last updated 2026-05-07. Licensed MIT.
Use cases
- Run document extraction and OCR tasks directly from an IDE or terminal
- Generate or complete code with Codestral FIM during development
- Execute durable workflows and process audio using Voxtral from supported editors
Pros
- Covers multiple Mistral AI features in one server
- Works with several popular IDEs and coding assistants
- TypeScript codebase makes contributions and customization accessible
Cons
- Very early stage with only 6 GitHub stars, limited community validation
- No information about stability or ongoing maintenance
- Requires Mistral API key and external dependencies for full functionality
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Covers multiple Mistral AI features in one server
- Works with several popular IDEs and coding assistants
- TypeScript codebase makes contributions and customization accessible
Cons
- Very early stage with only 6 GitHub stars, limited community validation
- No information about stability or ongoing maintenance
- Requires Mistral API key and external dependencies for full functionality
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Claude Code
Anthropic
Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.
Cursor
Anysphere
The AI-first code editor. Tab to autocomplete, Composer to multi-file refactor, Agents for the long-running stuff.