benzsevern/devpilot
Dev server supervisor for AI coders. CLI + MCP server with 10 tools. Manage lifecycles, detect reloads, check health, recover from crashes.
Platform-specific configuration:
{
"mcpServers": {
"devpilot": {
"command": "npx",
"args": [
"-y",
"devpilot"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Dev server supervisor for AI coders.
AI coding agents (Claude Code, Cursor, Copilot) break dev servers constantly — editing files mid-reload, causing port conflicts, spawning zombie processes. Then they panic: kill random PIDs, rotate ports, nuke all Python processes. It gets worse.
devpilot gives AI coders structured, reliable process awareness. It manages dev server lifecycles, detects reloads, checks health, and returns JSON that AI can parse and act on — so the panic cycle never starts.
DevPilot runs as a local MCP server because it needs direct access to your machine's processes, ports, and filesystem. Install once, and every AI session has the tools available.
Claude Code:
pip install "devpilot-ai[mcp]"
claude mcp add devpilot -- devpilot-mcpCursor / VS Code / other MCP clients:
{
"mcpServers": {
"devpilot": {
"command": "devpilot-mcp"
}
}
}> Why local, not remote? DevPilot spawns processes, reads stdout, checks localhost ports, and manages PIDs on your machine. A remote server can't do any of that. The Smithery listing exists for discovery and documentation — actual usage requires the local server.
pip install devpilot-aiOr with pipx for global CLI use:
pipx install devpilot-aidevpilot initScans for pyproject.toml, requirements.txt, package.json and generates .devpilot.yaml with the right framework profiles.
devpilot run api "uvicorn main:app --reload --port 8000"devpilot attach api --port 8000devpilot changed src/main.pyReturns structured JSON:
[{
"service": "api",
"relLoading reviews...