GitHub MCP Client for Docker GMU Server

Created By
devendershekhawata year ago
MCP (Model Context Protocol) client for GitHub Multi-User Server with Claude integration. Interactive chat interface for GitHub operations using natural language.
Overview

what is GitHub MCP Client for Docker GMU Server?

GitHub MCP Client is a Model Context Protocol (MCP) client designed to connect to the GitHub Multi-User Server (GMU) running in Docker, providing an interactive chat interface for GitHub operations using natural language queries powered by Claude.

how to use GitHub MCP Client?

To use the GitHub MCP Client, ensure the GMU server is running in Docker, install the necessary dependencies, configure your environment variables with your GitHub Personal Access Token and Anthropic API Key, and then run the interactive client to start querying GitHub operations.

key features of GitHub MCP Client?

  • Docker integration for seamless server connection
  • AI-powered natural language processing for GitHub queries
  • Multi-user support with individual GitHub Personal Access Tokens
  • Full access to GitHub API functionalities
  • Interactive chat interface for user-friendly operations

use cases of GitHub MCP Client?

  1. Querying user information from GitHub
  2. Managing repositories, issues, and pull requests through natural language
  3. Searching for repositories based on specific criteria
  4. Automating GitHub operations in a multi-user environment

FAQ from GitHub MCP Client?

  • What is required to run the GitHub MCP Client?

You need Docker, Python 3.13+, a GitHub Personal Access Token, and an Anthropic API Key.

  • Can I use this client for multiple GitHub accounts?

Yes! The client supports multi-user functionality with individual tokens.

  • How does the natural language processing work?

The client uses Claude to interpret user queries and determine the appropriate GitHub tools to execute.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
devendershekhawat
Star
0
Language
Python
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago