← Top 100 Full directory (1,563)

DevPilot

AI & Memory Remote ★ 2,649 10 tools

Dev server supervisor for AI coders. Manages dev server lifecycles, detects reloads, checks health, and recovers from crashes. 10 MCP tools for full lifecycle management. Best used as a local stdio server (pip install devpilot-ai[mcp]) since it needs access to your machine processes and ports.

Connect

MCP endpoint

https://devpilot--benzsevern.run.tools

How to connect

Smithery (hosted)

1. Open https://smithery.ai/servers/benzsevern/devpilot
2. Click Connect and complete OAuth in your MCP client (Claude, Cursor, VS Code, etc.)
3. MCP endpoint: https://devpilot--benzsevern.run.tools

Tools (10)

devpilot_status
Check health status of dev server services. Returns live health check results including status, response time, and configuration for all registered services or a specific one. Args: service_name: Name of a specific service to check. Omit to check all.
devpilot_changed
Report a file change and check if the dev server reloaded successfully. Call this AFTER editing a file. Returns which service was affected, reload status (reloaded/reload_failed/timeout), and health. This is the primary feedback loop for AI coders. Args: filepath: Path of the changed file relative to project root. verify_endpoint: Optional HTTP endpoint to hit after reload, e.g. "/api/hello". timeout: Max seconds to wait for reload detection. Default 15.
devpilot_run
Start and manage a dev server process. Spawns the process, captures stdout, detects reload patterns, monitors health, and auto-recovers from crashes. Supports FastAPI, Flask, Django, Vite, Next.js, and CRA with auto-detected defaults. Args: name: Unique service name, e.g. "api" or "frontend". cmd: Shell command to start the server, e.g. "uvicorn main:app --reload --port 8000". port: Port the server listens on. Auto-detected from framework if omitted. service_
devpilot_attach
Attach to an already-running dev server for health monitoring. Discovers the process by port but does NOT own or restart it. Use when the server was started externally. Args: name: Unique service name. port: Port the existing server listens on. service_type: "backend" or "frontend". cmd: Original start command (for reference only). health_endpoint: HTTP path for health checks.
devpilot_stop
Gracefully stop managed dev server services. Only stops services that devpilot started. Never kills processes it didn't start. Args: name: Name of a specific service to stop. stop_all: Set true to stop all managed services.
devpilot_init
Auto-detect project structure and generate .devpilot.yaml config. Scans for pyproject.toml, requirements.txt, and package.json to detect frameworks (FastAPI, Flask, Django, Vite, Next.js, CRA) and generates appropriate service configuration.
devpilot_up
Start all services defined in .devpilot.yaml. Reads the project config and starts each service under supervision with auto-recovery.
devpilot_log
View recent devpilot events including auto-restarts, crashes, recoveries, and escalations. Args: service_name: Filter to a specific service. Omit for all events.
devpilot_cleanup
Remove stale state entries for processes that are no longer running. Cleans up dead PIDs and orphan service registrations.
devpilot_health_check
Perform a direct health check on any port. Returns healthy/unhealthy status, HTTP status code, and response time. Works without registering a service. Args: port: Port number to check. endpoint: HTTP path like "/health". Uses raw TCP check if omitted.