cursor-mcp-guide
Model Context Protocol (MCP) is a standardized protocol that enables seamless communication between AI agents and various tools and services.
Understanding MCP (Model Context Protocol) and GitHub Integration
What is MCP?
Model Context Protocol (MCP) is a revolutionary standardized protocol that enables AI agents to communicate seamlessly with various tools and services. Think of it like a universal translator:
- Without MCP: Each tool speaks its own language, making it difficult for AI agents to integrate with multiple tools.
- With MCP: All tools speak the same language, allowing easy integration and communication.
Real-World Analogy
Imagine having ten expert consultants, each speaking a different language:
- Without MCP: You'd need ten different translators
- With MCP: Everyone speaks a common language, making collaboration effortless
This standardization allows AI agents to:
- Connect to databases
- Interact with GitHub
- Access cloud services
- Manage files and documents
- And much more!
GitHub MCP Features
The GitHub MCP integration provides powerful capabilities for interacting with GitHub repositories:
Repository Management
- Create new repositories
- Fork existing repositories
- Clone repositories
- Manage branches
- Create and merge pull requests
Code Operations
- Search through code
- Create and edit files
- Commit changes
- Review pull requests
- Add comments and reviews
Issue Management
- Create and update issues
- Add comments to issues
- Search through issues
- Apply labels and assignees
- Track milestones
Collaboration Features
- Manage project boards
- Handle discussions
- Review comments
- Manage repository settings
- Control access permissions
Installation Guide
Prerequisites: Node.js Setup
- Visit Node.js website
- Download the appropriate version:
- For M1/M2 Macs: macOS ARM64
- For Intel Macs: macOS x64
- Run the installer and follow the prompts
Installing GitHub MCP
Method 1: Using Smithery CLI (Recommended)
npx -y @smithery/cli@latest install @smithery-ai/github \
--client cursor \
--config '{"githubPersonalAccessToken":"your_token_here"}'
Method 2: Manual Configuration
- Open
~/.cursor/mcp.json
- Add the following configuration:
{
"mcp_servers": {
"github": {
"command": "npx @smithery/github-mcp --token your_github_token"
}
}
}
Finding MCP Servers on Smithery
- Visit Smithery
- Browse available MCP servers:
- Filter by category
- Sort by popularity
- Search by name or functionality
- Select "GitHub MCP" from the list
- Follow installation instructions
Adding to Cursor
Method 1: Command Line Installation
# Using Smithery CLI
npx @smithery/cli install @smithery-ai/github
Method 2: Manual Configuration
-
Open Cursor Settings:
- Use
⌘ + Shift + P
(macOS) orCtrl + Shift + P
(Windows) - Type "Cursor Settings"
- Select "MCP"
- Use
-
Add MCP Server:
- Click "Add new global MCP server"
- Configure using the provided JSON structure
Method 3: Direct JSON Configuration
- Navigate to
~/.cursor/mcp.json
- Add server configuration manually:
{
"mcp_servers": {
"github": {
"command": "npx @smithery/github-mcp --token your_github_token"
}
}
}
Using GitHub MCP
Once installed, you can use GitHub MCP to:
- Create and manage repositories
- Handle issues and pull requests
- Search through code
- Manage files and branches
- Collaborate with team members
Related MCP Servers
View all developer_tools servers →context7
by upstash
Context7 MCP provides up-to-date, version-specific documentation and code examples directly into your prompt, enhancing the capabilities of LLMs by ensuring they use the latest information.
Sequential Thinking
by modelcontextprotocol
An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.
git-mcp
by idosal
GitMCP is a free, open-source, remote Model Context Protocol (MCP) server that transforms GitHub projects into documentation hubs, enabling AI tools to access up-to-date documentation and code.
Everything MCP Server
by modelcontextprotocol
The Everything MCP Server is a comprehensive test server designed to demonstrate the full capabilities of the Model Context Protocol (MCP). It is not intended for production use but serves as a valuable tool for developers building MCP clients.
exa-mcp-server
by exa-labs
A Model Context Protocol (MCP) server allows AI assistants to use the Exa AI Search API for real-time web searches in a secure manner.
repomix
by yamadashy
Repomix is a tool that packs your codebase into AI-friendly formats, making it easier to use with AI tools like LLMs.
mcpdoc
by langchain-ai
MCP LLMS-TXT Documentation Server provides a structured way to manage and retrieve LLM documentation using the Model Context Protocol.