GitHub MCP Server: Complete Setup and Usage Guide 2026
Let AI access and manage your GitHub repositories - step-by-step guide to GitHub MCP Server
GitHub MCP Server: Complete Setup and Usage Guide 2026
Let AI access and manage your GitHub repositories - step-by-step guide to GitHub MCP Server
GitHub MCP Server: Complete Guide 2026 What is GitHub MCP Server? **GitHub MCP Server** is an MCP (Model Context Protocol) server that enables AI assistants to Let AI access and manage your GitHub repositories. MCP is an open protocol that standard
GitHub MCP Server: Complete Guide 2026
What is GitHub MCP Server?
GitHub MCP Server is an MCP (Model Context Protocol) server that enables AI assistants to Let AI access and manage your GitHub repositories. MCP is an open protocol that standardizes how AI models interact with external tools and data sources.
Prerequisites
Installation
Option 1: NPM (Recommended)
bash
npm install -g @development/github-mcp-server-mcp
Option 2: From Source
bash
git clone https://github.com/modelcontextprotocol/github-mcp-server-mcp
cd github-mcp-server-mcp
npm install
npm run build
Configuration
Claude Desktop Setup
Edit your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
json
{
"mcpServers": {
"github-mcp-server": {
"command": "npx",
"args": [
"-y",
"@development/github-mcp-server-mcp"
],
"env": {
"GITHUB_MCP_SERVER_API_KEY": "your-api-key-here",
"DEBUG": "false"
}
}
}
}
Environment Variables
bash
Required
export GITHUB_MCP_SERVER_API_KEY=your_key_hereOptional
export GITHUB_MCP_SERVER_TIMEOUT=30
export GITHUB_MCP_SERVER_MAX_RESULTS=50
Available Tools
After installation, Claude has access to these tools:
Core Tools
github_mcp_server_list
Description: List available resources
Parameters: { limit: number, filter: string }github_mcp_server_get
Description: Get specific resource by ID or name
Parameters: { id: string }github_mcp_server_create
Description: Create a new resource
Parameters: { name: string, content: any }github_mcp_server_update
Description: Update existing resource
Parameters: { id: string, updates: any }github_mcp_server_delete
Description: Delete a resource
Parameters: { id: string, confirm: boolean }
Usage Examples
Example 1: Basic Usage in Claude
Once configured, you can ask Claude naturally:
You: "Use GitHub MCP Server to help me with Let AI access and manage your GitHub repositories"Claude: "I'll use the GitHub MCP Server MCP server to help you.
[Uses github_mcp_server_list tool]
Here's what I found..."
Example 2: Complex Workflow
You: "Please analyze my development setup and suggest improvements"Claude will:
List all resources using GitHub MCP Server
Analyze the current configuration
Identify opportunities for improvement
Suggest specific changes with reasoning
Building a Custom MCP Server
You can also build your own MCP server:
typescript
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import {
CallToolRequestSchema,
ListToolsRequestSchema,
} from "@modelcontextprotocol/sdk/types.js";const server = new Server(
{
name: "my-development-server",
version: "0.1.0",
},
{
capabilities: {
tools: {},
},
}
);
// Define available tools
server.setRequestHandler(ListToolsRequestSchema, async () => {
return {
tools: [
{
name: "development_query",
description: "Let AI access and manage your GitHub repositories",
inputSchema: {
type: "object",
properties: {
query: {
type: "string",
description: "Your query"
}
},
required: ["query"]
}
}
]
};
});
// Handle tool calls
server.setRequestHandler(CallToolRequestSchema, async (request) => {
if (request.params.name === "development_query") {
const { query } = request.params.arguments as { query: string };
// Your implementation here
const result = await performQuery(query);
return {
content: [
{
type: "text",
text: JSON.stringify(result, null, 2)
}
]
};
}
throw new Error(Unknown tool: ${request.params.name});
});
// Start server
const transport = new StdioServerTransport();
await server.connect(transport);
Troubleshooting
Common Issues
Issue: Server not starting
bash
Check if node is properly installed
node --version # Should be 18+Reinstall the package
npm install -g @development/github-mcp-server-mcp --force
Issue: Authentication failing
bash
Verify your API key
echo $GITHUB_MCP_SERVER_API_KEYTest API key validity
curl -H "Authorization: Bearer $GITHUB_MCP_SERVER_API_KEY" https://api.github.com/v1/test
Issue: Claude Desktop not recognizing server
Security Considerations
bash
Use environment-specific keys (never hardcode)
In production, use a secrets manager
export GITHUB_MCP_SERVER_API_KEY=$(aws secretsmanager get-secret-value --secret-id mcp-keys --query SecretString --output text | jq -r '.development_key')Limit MCP server permissions to minimum required
Use read-only tokens when possible
Conclusion
GitHub MCP Server unlocks the ability to Let AI access and manage your GitHub repositories directly through your AI assistant. This makes complex development tasks dramatically faster and more intuitive.
As MCP becomes the standard for AI tool integration, mastering these servers gives you a significant productivity advantage.
*GitHub MCP Server MCP setup guide | May 2026*
相关工具
相关教程
Enable AI to interact with Slack channels - step-by-step guide to Slack MCP Server
Query and manage databases with natural language - step-by-step guide to Postgres MCP Server
Give AI agents access to your local files - step-by-step guide to Filesystem MCP Server
Manage project issues with AI assistance - step-by-step guide to Linear MCP Server
Process payments and manage subscriptions via AI - step-by-step guide to Stripe MCP Server
Access and manage Google Drive documents with AI - step-by-step guide to Google Drive MCP