GitHub Repository Manager MCP Server
Enables AI assistants to create and delete GitHub repositories with customizable settings through the Model Context Protocol, supporting both public and private repositories with secure token-based authentication.
README
GitHub Repository Manager MCP Server
A Model Context Protocol (MCP) server that allows AI assistants to create and delete GitHub repositories.
Features
- ✅ Create GitHub repositories with customizable settings
- ✅ Delete GitHub repositories (permanent deletion)
- ✅ MCP protocol compliant - works with Claude Desktop and other MCP clients
- ✅ Simple setup - just configure and restart your AI assistant
- ✅ Secure - uses environment variables for sensitive data
Quick Start
1. Install Dependencies
pip install -r requirements.txt
2. Set Up Your GitHub Token
- Go to GitHub Settings > Tokens
- Generate a new token with "repo" permissions
- Copy the token
3. Create Environment File
Create a .env file in the same directory as simple_mcp_server.py:
# .env file
GITHUB_TOKEN=your_actual_github_token_here
⚠️ Important: Never commit your .env file to Git! It contains sensitive information.
4. Configure Claude Desktop
- Open:
~/Library/Application Support/Claude/config.json - Replace the content with:
{
"darkMode": "dark",
"scale": 0,
"mcpServers": {
"github-repo-creator": {
"command": "python3",
"args": ["/path/to/your/simple_mcp_server.py"],
"env": {}
}
}
}
Note: No need to set GITHUB_TOKEN in the config anymore - it's loaded from the .env file.
5. Restart Claude Desktop
- Quit and reopen Claude Desktop
6. Test It!
Ask Claude:
- "What tools do you have available?"
- "Create a repository called 'my-test-repo'"
- "Delete the repository called 'my-test-repo'"
Available Tools
create_github_repository
Creates a new GitHub repository.
Parameters:
name(required): Repository nameprivate(optional): Make it private (default: false)description(optional): Repository descriptionauto_init(optional): Initialize with README (default: true)
delete_github_repository
Deletes an existing GitHub repository.
Parameters:
name(required): Repository name to delete
Files
simple_mcp_server.py- The MCP server implementationrequirements.txt- Python dependenciesclaude_config_example.json- Example Claude Desktop configuration.env.example- Example environment file (copy to.envand add your token)README.md- This file
Security Notes
- ⚠️ Never commit your
.envfile to Git - ⚠️ Never commit your real GitHub token to Git
- ⚠️ Repository deletion is permanent
- ✅ Use environment variables for sensitive data
- ✅ Regularly rotate your tokens
- ✅ Add
.envto your.gitignorefile
Environment Variables
The server uses these environment variables:
GITHUB_TOKEN- Your GitHub personal access token (required)
Troubleshooting
"GITHUB_TOKEN not found" error
- Make sure you created a
.envfile - Check that
GITHUB_TOKEN=your_tokenis in the.envfile - Ensure the
.envfile is in the same directory assimple_mcp_server.py
"Repository not found" error
- Check that the repository name is correct (case-sensitive)
- Ensure your token has the right permissions
- Verify the repository exists in your account
MCP server not loading
- Check the file path in your config
- Ensure the script is executable:
chmod +x simple_mcp_server.py - Restart Claude Desktop after config changes
Example Usage
Once configured, you can ask Claude:
- "Create a private repository called 'secret-project' with description 'My secret project'"
- "Make a public repository named 'open-source-tool'"
- "Delete the repository called 'old-test-repo'"
- "What tools do you have available?"
License
MIT License - feel free to use and modify! # MCP-Repo-Manager-
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.