JetBrains MCP Proxy Server

About this MCP

The JetBrains MCP Proxy Server enables seamless integration between AI assistants and JetBrains IDEs like IntelliJ IDEA, PyCharm, WebStorm, and Android Studio. It acts as a bridge that allows AI models to access and interact with your development environment, providing context-aware assistance directly within your coding workflow. This integration enhances productivity by allowing AI tools to understand your project structure, code, and development context.

Documentation

Overview

The JetBrains MCP Proxy Server enables AI assistants to interact with JetBrains IDEs by proxying requests between them. This allows AI models to access your code, project structure, and other IDE context to provide more relevant assistance.

Installation

Step 1: Install the MCP Server Plugin in your JetBrains IDE

Open your JetBrains IDE (IntelliJ IDEA, PyCharm, WebStorm, etc.)
Go to Settings/Preferences → Plugins
Click on "Marketplace" and search for "MCP Server"
Install the plugin from: https://plugins.jetbrains.com/plugin/26071-mcp-server
Restart your IDE when prompted

Step 2: Set up the MCP Proxy

You can use the proxy with npm/npx:

# Install globally
npm install -g @jetbrains/mcp-proxy

# Or use directly with npx
npx -y @jetbrains/mcp-proxy

Configuration with AI Assistants

Claude Desktop Integration

To use with Claude Desktop, add the following to your claude_desktop_config.json:

On macOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "jetbrains": {
      "command": "npx",
      "args": ["-y", "@jetbrains/mcp-proxy"]
    }
  }
}

Advanced Configuration Options

If you're running multiple IDEs with the MCP server and want to connect to a specific one, add to your MCP server configuration:

"env": {
  "IDE_PORT": "<port of IDE's built-in webserver>"
}

To specify a different address/host (default is 127.0.0.1):

"env": {
  "HOST": "<host/address of IDE's built-in webserver>"
}

To enable logging:

"env": {
  "LOG_ENABLED": "true"
}

Building from Source

If you prefer to build the proxy from source:

Clone the repository: git clone https://github.com/JetBrains/mcp-jetbrains.git
Install dependencies: pnpm install
Build the project: pnpm build

Usage

Once configured, AI assistants that support the Model Context Protocol can:

Access your project files and structure
Understand the code context you're working in
Provide more relevant suggestions and assistance
Execute IDE commands when appropriate

The MCP server runs in the background, facilitating communication between your AI assistant and the JetBrains IDE.

Troubleshooting

Ensure the MCP Server plugin is installed and enabled in your IDE
Check that your IDE is running before starting the AI assistant
Verify the correct port is configured if using multiple IDEs
Enable logging for more detailed information about connection issues