drio
Open app

Speakeasy

Source

Catalog onlyCatalog onlySTDIO

Overview

Speakeasy is a TypeScript-based MCP server example that allows developers to build APIs that users love, specifically designed for chatting with the Mistral AI platform.

To use Speakeasy, you need to set up the server by installing dependencies, configuring your Mistral API key, and adding the server configuration to your MCP client (like the Claude desktop app).

  • Provides two tools for chatting with Mistral: text input and text/image input. - Supports the Model Context Protocol (MCP). - Easy setup with clear instructions for installation and configuration.
  1. Building interactive chat applications using Mistral AI.
  2. Integrating Mistral AI capabilities into existing applications.
  3. Developing custom tools for enhanced user interaction with AI.

Add to your AI client

Use these steps to connect Speakeasy in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mistral-mcp-server-example-speakeasy-api": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mistral-mcp-server-example-speakeasy-api"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mistral-mcp-server-example-speakeasy-api": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mistral-mcp-server-example-speakeasy-api"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mistral-mcp-server-example-speakeasy-api": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mistral-mcp-server-example-speakeasy-api"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mistral-mcp-server-example-speakeasy-api": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mistral-mcp-server-example-speakeasy-api"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mistral-mcp-server-example-speakeasy-api": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mistral-mcp-server-example-speakeasy-api"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mistral-mcp-server-example-speakeasy-api": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mistral-mcp-server-example-speakeasy-api"
      ]
    }
  }
}

FAQ

What is required to run Speakeasy?

You need Node.js and an MCP client that supports tools.

How do I get an API key for Mistral?

You can sign up at mistral.ai to obtain your API key.

Can I use Speakeasy with any MCP client?

Yes, as long as the client supports the Model Context Protocol.