DevServer MCP

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 bothALPHAsoftware 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 v0.6.0

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 adevservers.ymlfile 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 autostart: true worker: command: 'celery -A myproject worker -l info' working_dir: '.' port: 5555 prefix_logs: false # Optional: Enable experimental Playwright browser automation experimental: playwright: true

{ "servers": { "devserver": { "url": "http://localhost:3001/mcp/", "type": "http" } } }

Then run the TUI in a separate terminal:devservers

claude mcp add --transport http devservers http://localhost:3001/mcp/

..or for a project (which saves it to a.mcp.jsonin the project):

claude mcp add -s project --transport http devservers http://localhost:3001/mcp/

Then run the TUI in a separate terminal:devservers

Add the server configuration insettings.json(~/.gemini/settings.jsonglobally or.gemini/settings.jsonper project,see docs):

... "mcpServers": { "devservers": { "httpUrl": "http://localhost:3001/mcp", "timeout": 5000, "trust": true } }, ...

Zed doesn't yet support remote MCP servers natively so you need to use a proxy likemcp-proxy.

"context_servers": { "devservers": { "command": { "path": "uvx", "args": ["mcp-proxy", "--transport", "streamablehttp", "http://localhost:3001/mcp/"] } } },

Then run the TUI in a separate 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_devserver_statuses()- Get all server statuses
- get_devserver_logs(name, offset, limit, reverse)- Get logs with pagination support

- offset: Starting position (default: 0, negative values count from end)
- limit: Maximum logs to return (default: 100)
- reverse: True for newest first, False for oldest first (default: True)

Whenexperimental.playwrightis 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, offset, limit, reverse)- Get console messages with pagination

- clear: Clear messages after retrieval (default: False)
- offset: Starting position (default: 0, negative values count from end)
- limit: Maximum messages to return (default: 100)
- reverse: True for newest first, False for oldest first (default: True)

- full_page: Capture full page instead of viewport (default: False)
- name: Optional filename for the screenshot (default: timestamped name)
- 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

- Followunessa.net on Blueskyor@uninen on Twitter
- Read my continuously updating learnings from Vite / Vue / TypeScript and other Web development topics from myToday I Learned site

Contributions are welcome! Please follow thecode of conductwhen interacting with others.

CodeVF MCP lets AI hand off problems to real engineers instantly, so your workflows don’t stall when models hit their limits.