Aider MCP WebSocket Server
About
WebSocket server that exposes Aider's AI coding capabilities through the Model Context Protocol (MCP) for programmatic access
Details
- Author
- larock22
- Downloads
- 362
- Categories
- Other
Jump to
- Full MCP protocol support with standard JSON-RPC 2.0 methods
- Multi-tenant isolation: one Aider child process per client
- Automatic completion detection (waits for Aider to finish)
- Isolated workspace directories per session
- Real-time bidirectional WebSocket communication
- Environment variable and CLI argument configuration
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Aider MCP WebSocket ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install dependencies with npm install, copy .env.example to .env and add your OpenAI API key. Start the recommended MCP server with npm run mcp, then connect via WebSocket using JSON-RPC 2.0. The server exposes tools such as aider_command, aider_add_file, and aider_run_command. Client code examples for WebSocket connection and tool calls are provided in the README.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"aider mcp websocket server": {
"aider-mcp": {
"command": "python3",
"args": [
"test-debug.py"
]
}
}
}
}
McpServers
{
"aider-mcp": {
"command": "python3",
"args": [
"test-debug.py"
]
}
}
Aider MCP WebSocket Server
Quick Start
This is a real MCP (Model Context Protocol) server that lets you control Aider programmatically via WebSocket. It's like having Aider as an API.
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



