Mistral MCP Server

Integrations

  • Used for environment variable management, specifically for storing the Mistral API key.

  • Supported platform for running the MCP server with the Claude desktop application.

  • Used as the runtime environment for the MCP server, specifically tested on v20.17.10.

Mistral MCP server example

This is a TypeScript-based MCP server that provides two tools for chatting with Mistral. It is a basic example of how to create a server that can be used with the Model Context Protocol (MCP).

Blog post

This repository is part of a blog post by Speakeasy: Building an MCP server for Mistral.

Requirements

Mistral API key

To interact with the Mistral AI platform, you'll need an API key. You can get one by signing up at mistral.ai.

Set your API key as an environment variable. Create a copy of .env.example and rename it .env.

cp .env.example .env open .env

Now update the .env file with your Mistral API key:

MISTRAL_API_KEY="YOUR_MISTRAL_API_KEY"

Tools

This server provides two tools.

For chatting with Mistral using text input, the mistral_chat_text tool:

  • Takes a model and an array of text inputs
  • Returns a text response from Mistral.

For chatting with Mistral using text and image input, the mistral_chat_image tool:

  • Takes a model and an array of text and image inputs
  • Only accepts images hosted on a public URL
  • Returns a text response from Mistral

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use this server with the Claude desktop app, add the following server config to your Claude config file:

  • On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • On Windows: %APPDATA%/Claude/claude_desktop_config.json
{ "mcpServers": { "Mistral MCP Server": { "command": "node", "args": [ // Update this path to the location of the built server "/Users/speakeasy/server-mistral/build/index.js" ], "env": { // Update this with your Mistral API key "MISTRAL_API_KEY": "YOUR_MISTRAL_API_KEY" } } } }

Debugging

Since MCP servers communicate through standard input/output streams (stdio), debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The MCP Inspector will provide a URL for accessing debugging tools in your browser.

License

This project is licensed under the MIT License - see the LICENSE file for details.

-
security - not tested
A
license - permissive license
-
quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

A TypeScript-based MCP server that provides two tools for chatting with Mistral AI models, supporting both text-only conversations and image+text inputs.

  1. Blog post
    1. Requirements
      1. Mistral API key
        1. Tools
          1. Development
            1. Installation
              1. Debugging
            2. License

              Related MCP Servers

              • -
                security
                F
                license
                -
                quality
                An MCP server that enables AI assistants like Claude to interact with Anki flashcard decks, allowing users to create, manage, and update flashcards through natural language conversations.
                Last updated -
                1
                TypeScript
              • -
                security
                -
                license
                -
                quality
                An MCP-based messaging system that allows AI systems to interact with various messaging platforms through standardized tools for sending text, images, documents, buttons, and alerts.
                Last updated -
                Python
              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol (MCP) server that enables real-time, interactive AI chat with Selector AI through a streaming-capable server and Docker-based client communicating via stdin/stdout.
                Last updated -
                1
                Python
                Apache 2.0
              • -
                security
                A
                license
                -
                quality
                An MCP-based service that enables AI models to seamlessly interact with Feishu (Lark) platform, supporting document reading and chatbot messaging capabilities.
                Last updated -
                396
                3
                TypeScript
                MIT License
                • Linux
                • Apple

              View all related MCP servers

              ID: cnz4nubw46