Github-Oauth MCP Server
発達
環境を設定する
まず、uv をインストールし、Python プロジェクトと環境を設定しましょう。
MacOS/Linux : curl -LsSf https://astral.sh/uv/install.sh | sh
Windows : powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"uv コマンドが確実に実行されるように、後でターミナルを再起動してください。
それでは、プロジェクトを作成して設定しましょう。
ローカルのクロードデスクトップアプリを実行中
ツールを登録するには、claude_desktop_config.json を更新する必要があることを確認してください。
Related MCP server: GitHub Integration Hub
claude_desktop_config.json は次の場所にあります:
For Windows : code $env:AppData\Claude\claude_desktop_config.json
For Mac/Linux :code ~/Library/Application\ Support/Claude/claude_desktop_config.json{
"mcpServers": {
"Github-Oauth": {
"command": "C:\\Users\\Hp\\.local\\bin\\uv",
"args": [
"--directory",
"C:\\Users\\Hp\\Github-Oauth\\src\\github_oauth",
"run",
"server.py"
]
}
}
}デバッグ
MCPサーバーはstdio経由で実行されるため、デバッグが困難になる場合があります。最適なデバッグ環境を実現するには、 MCP Inspectorの使用を強くお勧めします。
次のコマンドを使用して、 npm経由で MCP Inspector を起動できます。
npx @modelcontextprotocol/inspector uv --directory C:\Users\Hp\Github-Oauth run github-oauth起動すると、ブラウザでアクセスしてデバッグを開始できる URL がインスペクタに表示されます。
Available Tools
4 toolsauthorize_githubB
Generate GitHub authorization URL for user authorization.
Inputs: no named parameters.
get_access_token_from_codeC
Exchange authorization code for an access token.
Inputs: code (required).
get_user_profileB
Fetch the authenticated user's GitHub profile.
Inputs: no named parameters.
get_user_repositoriesB
Fetch the repositories of the authenticated user.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose in the OAuth flow and user data retrieval: authorize_github initiates the flow, get_access_token_from_code handles token exchange, get_user_profile fetches profile data, and get_user_repositories fetches repositories. There is no overlap or ambiguity between these operations.
All tools follow a consistent verb_noun pattern with snake_case (e.g., authorize_github, get_access_token_from_code). The naming is predictable and readable throughout the set.
With 4 tools, this server is well-scoped for its purpose of GitHub OAuth authentication and basic user data access. Each tool earns its place by covering essential steps in the OAuth flow and common user queries.
The tool set covers the core OAuth flow (authorization, token exchange) and basic user data (profile, repositories), with no dead ends. A minor gap exists in lacking tools for more advanced GitHub operations (e.g., repository management or issue handling), but this is reasonable given the server's focused scope.
Related MCP Connectors
Access the GitHub API, enabling file operations, repository management, search functionality, and…
Manage repositories, users, releases, and automate GitHub workflows
OAuth Multi-LLM Orchestrator
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables access to GitHub repositories and data through the GitHub API. Supports retrieving repositories, issues, pull requests, and searching code across GitHub with authentication via personal access tokens.-
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to interact with GitHub through OAuth-authenticated operations including starting authorization flows, listing repositories, and creating issues using stored access tokens.1MIT
- FlicenseNot gradedqualityDmaintenanceConnects Claude to GitHub via OAuth and proxies official GitHub MCP tools, allowing each end user to interact with GitHub as themselves.-
- FlicenseNot gradedqualityCmaintenanceEnables claude.ai to connect to GitHub MCP using OAuth, providing full toolset for repository, issue, PR, Actions, and gist operations.-