What GitHub permissions are required?
The personal access token needs `repo` (for repository access) and `user` (for user information) scopes.
@Joseph19820124
Basic information
A GitHub MCP server demo with create repository functionality
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"joseph-github-mcp-server": {
"command": "python",
"args": [
"main.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
The GitHub MCP Server is a Model Context Protocol (MCP) server that provides GitHub repository creation functionality. It allows AI applications and other MCP clients to programmatically create new GitHub repositories with customizable settings using the standard MCP protocol over stdin/stdout.
Clone the repository, install Python dependencies via pip install -r requirements.txt, set the GITHUB_TOKEN environment variable with a token that has repo and user scopes, then run python main.py. The server listens for JSON‑RPC 2.0 requests (e.g., tools/call with tool name create_repository) over stdio. Test it by sending echo '{"method": "tools/list", "id": "1"}' | python main.py.
The personal access token needs `repo` (for repository access) and `user` (for user information) scopes.
Set the token as an environment variable: `export GITHUB_TOKEN="your_github_personal_access_token"`.
Python 3.8 or higher is required.
The server runs as a subprocess communicating via JSON‑RPC 2.0 over stdio. MCP clients send `tools/list` and `tools/call` requests to discover and use the `create_repository` tool.
No, the `private` parameter defaults to `false`, making repositories public unless explicitly set to `true`.
MCP server for Atlassian tools (Confluence, Jira)
GitHub's official MCP Server
🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from https://github.com/nguyenvanduocit/all-in-one-model-context-protocol
Production-grade GitLab MCP server with 86 tools — full GitLab control from any AI agent (Claude, Cursor, Zed).
MCP servers for the Atlassian products (Bitbucket, Confluence, JIRA) of the Data Center version
Comments