What prerequisites are needed?
Node.js 18+, Aider installed and available in PATH (`pip install aider-chat`), and an OpenAI API key.
@larock22
Basic information
WebSocket server that exposes Aider's AI coding capabilities through the Model Context Protocol (MCP) for programmatic access
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"aider-mcp": {
"command": "python3",
"args": [
"test-debug.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A real MCP (Model Context Protocol) server that lets you control Aider programmatically via WebSocket, wrapping Aider’s functionality for use by editor plugins and services. It provides two server implementations: a standard MCP protocol server (recommended) and a custom WebSocket wrapper. It is for developers who want to send natural language commands to Aider from any MCP-compatible client, like Claude Desktop or custom apps.
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.
Node.js 18+, Aider installed and available in PATH (`pip install aider-chat`), and an OpenAI API key.
Each client gets an isolated workspace directory and a separate Aider process, ensuring session separation.
The custom WebSocket wrapper supports token-based authentication via the `VALID_TOKENS` environment variable (empty means no auth). The MCP server does not mention authentication.
Files are saved in directories under `workspaces/`, e.g., `workspaces/mcp-*/`. You can check them with `ls -la workspaces/`.
The MCP server includes smart completion detection that waits for Aider to finish (using a 3-second silence detection), solving the problem of premature responses.
A search tool helps dev to solve the naming things problem.
Hindsight: Agent Memory That Learns
🚀 The fast, Pythonic way to build MCP servers and clients.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
Comments