automcp
AutoMCP scaffolds your Model Context Protocol config from package.json deps
claude mcp add --transport stdio lirantal-automcp npx -y automcp
How to use
automcp is a CLI tool that auto-detects your coding agent (Cursor or VS Code) and scans your project's dependencies to automatically generate MCP (Model Context Protocol) server entries for GitMCP. It resolves each dependency to its GitHub repository and constructs GitMCP URLs, then updates your local MCP configuration without duplicating existing entries. You can run it in your project directory to apply changes, or use --dry-run to preview what would be added. The tool can target a specific agent or config location with --agent and --config, and it supports including development dependencies with --include-dev. After running, your MCP config will contain new servers like <dependency> Docs with their corresponding https://gitmcp.io/owner/repo URLs, ready to be consumed by your coding agents.
How to install
Prerequisites:
- Node.js (LTS) and npm installed on your system
- Access to the project directory where you want to add MCP entries
Install options:
- Run without installing globally (recommended):
# In your project directory
npx automcp
- Install as a development dependency in your project (also valid):
# In your project directory
npm add -D automcp
npx automcp
- Alternatively, install and run via package manager if you prefer a local install (optional):
npm install --save-dev automcp
node_modules/.bin/automcp
Prerequisites recap:
- Ensure you have write access to the project directory you’re updating
- Ensure your project contains a package.json with dependencies to analyze
- If behind a proxy or firewall, ensure npm can reach registry and GitHub for repository lookup
Additional notes
Tips and caveats:
- AutoMCP updates only local project configurations (e.g., .cursor/mcp.json or .vscode/mcp.json); it does not modify global agent configurations.
- If a dependency lacks a GitHub repository or a repository field, it will be skipped.
- Use --dry-run to safely preview changes before applying them.
- You can target a specific agent or config path with --agent and --config; these flags can be used independently or together.
- Duplicates are prevented by URL normalization; however, manually editing the config may still be necessary in edge cases.
- The generated MCP entries use the GitMCP URL format: https://gitmcp.io/owner/repo
Related MCP Servers
volcano-agent-sdk
🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.
mcp -code-execution-mode
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.
git
An MCP (Model Context Protocol) server enabling LLMs and AI agents to interact with Git repositories. Provides tools for comprehensive Git operations including clone, commit, branch, diff, log, status, push, pull, merge, rebase, worktree, tag management, and more, via the MCP standard. STDIO & HTTP.
decipher-research-agent
Turn topics, links, and files into AI-generated research notebooks — summarize, explore, and ask anything.
MediaWiki
Model Context Protocol (MCP) Server to connect your AI with any MediaWiki
symfony
A Symfony package designed for building secure servers based on the Model Context Protocol, utilizing Server-Sent Events (SSE) and/or StreamableHTTP for real-time communication. It offers a scalable tool system tailored for enterprise-grade applications.