A Model Context Protocol (MCP) server that manages development servers for LLM-assisted workflows. Provides programmatic control over multiple development servers through a unified interface with a simple TUI, plus experimental browser automation via Playwright.
You can also turn the servers on and off by clicking via the TUI.
This is both ALPHA software and an exercise in vibe coding; most of this codebase is written with the help of LLM tools.
The tests validate some of the functionality and the server is already useful if you happen to need the functionality but YMMV.
- 🚀 Process Management: Start, stop, and monitor multiple development servers
- 📊 Rich TUI: Interactive terminal interface with real-time log streaming
- 🌐 Browser Automation: Experimental Playwright integration for web testing and automation
- 🔧 LLM Integration: Full MCP protocol support for AI-assisted development workflows
uv add --dev git+https://github.com/Uninen/devserver-mcp.git --tag v0.3.2
If you want to use the experimental Playwright browser automation features, you must install Playwright manually:
# Install Playwright
uv add playwright
# Install browser drivers
playwright install
Create a devservers.yml
file in your project root:
servers:
backend:
command: 'python manage.py runserver'
working_dir: '.'
port: 8000
frontend:
command: 'npm run dev'
working_dir: './frontend'
port: 3000
worker:
command: 'celery -A myproject worker -l info'
working_dir: '.'
port: 5555
# Optional: Enable experimental Playwright browser automation
experimental:
playwright: true
Add to .vscode/mcp.json
:
{
"servers": {
"devserver": {
"url": "http://localhost:3001/mcp/",
"type": "http"
}
}
}
Run the TUI in a separate terminal: devservers
Install the server (as SSE because Claude Code doesn't yet support streamable http 🤦♂️):
claude mcp add --transport sse devserver http://localhost:3001/sse/
Run the TUI in a separate terminal in SSE mode: devservers --sse
Zed doesn't yet support remote MCP servers natively so you need to use a proxy and SSE mode.
You can either use the UI in Assistant Setting -> Context Server -> Add Custom Server, and add name "Devservers" and
command npx -y mcp-remote http://localhost:3001/sse/ --transport sse
, or, you can add this manually to Zed config:
"context_servers": {
"devservers": {
"command": {
"path": "npx",
"args": ["-y", "mcp-remote", "http://localhost:3001/sse/", "--transport", "sse"]
}
}
},
Run the TUI in a separate terminal in SSE mode: devservers --sse
Start the TUI in terminal:
devservers
Now you can watch and control the devservers and see the logs while also giving LLMs full access to the servers and their logs.
The server exposes the following tools for LLM interaction:
- start_server(name) - Start a configured server
- stop_server(name) - Stop a server (managed or external)
- get_server_status(name) - Get server status
- get_server_logs(name, lines) - Get recent logs from managed servers
When experimental.playwright
is set in config:
- browser_navigate(url, wait_until) - Navigate browser to URL with wait conditions
- browser_snapshot() - Capture accessibility snapshot of current page
- browser_console_messages(clear) - Get console messages with optional clear
- Start the server:
devservers
- Start MCP Inspector:
npx @modelcontextprotocol/inspector http://localhost:3001
- Start the server:
devservers
- Use MCP Inspector in CLI mode, for example:
npx @modelcontextprotocol/inspector --cli http://localhost:3001 --method tools/call --tool-name start_server --tool-arg name=frontend
- Follow unessa.net on Bluesky or @uninen on Twitter
- Read my continuously updating learnings from Vite / Vue / TypeScript and other Web development topics from my Today I Learned site
Contributions are welcome! Please follow the code of conduct when interacting with others.