Mistral AI MCP server

This MCP server for Mistral provides tools for chatting with Mistral AI models through the Model Context Protocol (MCP). It enables interaction with Mistral's language models using either text-only or text-and-image inputs, making it easy to integrate Mistral's capabilities into compatible MCP clients.

Requirements

• Node.js (tested on v20.17.10)
• An MCP client that supports tools - recommended options:
  • Claude desktop application
  • Cline VSCode extension
• Mistral API key

Setting Up Your API Key

To use this server, you'll need a Mistral AI API key:

1. Sign up at mistral.ai to obtain your API key
2. Create your environment file:

cp .env.example .env

3. Edit the .env file to add your API key:

MISTRAL_API_KEY="YOUR_MISTRAL_API_KEY"

Installation

1. Install dependencies:

npm install

2. Build the server:

npm run build

3. Configure your Claude desktop app to use the server:

Edit your Claude config file located at:

• MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%/Claude/claude_desktop_config.json

Add the following server configuration:

{
  "mcpServers": {
    "Mistral MCP Server": {
      "command": "node",
      "args": [
        "/path/to/your/server-mistral/build/index.js"
      ],
      "env": {
        "MISTRAL_API_KEY": "YOUR_MISTRAL_API_KEY"
      }
    }
  }
}

Be sure to update the path and API key with your actual values.

Available Tools

Text-Only Chat Tool

The mistral_chat_text tool allows for text conversations with Mistral models:

• Input: A model name and an array of text inputs
• Output: Text response generated by the specified Mistral model

Image and Text Chat Tool

The mistral_chat_image tool enables multimodal conversations:

• Input: A model name and an array containing both text and image inputs
• Note: Images must be hosted on a public URL
• Output: Text response from the Mistral model that considers both the text and visual content

Troubleshooting

If you encounter issues, you can use the MCP Inspector for debugging:

npm run inspector

This will provide a browser URL where you can access debugging tools to inspect the communication between your MCP client and the server.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.