# GitHub MCP Server Official GitHub Model Context Protocol server that connects AI agents to GitHub repositories, issues, pull requests, and code. ## Agent Decision Summary - Risk level: elevated - Source confidence: high - Recommended workflows: Coding agent workflow, Connector or protocol layer - Permission surface: shell/files, memory, external services - Agent JSON: https://www.openagent.bot/plugins/github-mcp-server.agent.json ## Summary GitHub MCP Server is the official Model Context Protocol server from GitHub that lets AI agents browse repositories, create and manage issues, review pull requests, search code, and interact with GitHub's API through standardized MCP tool calls. ## Guide ### FAQ - What is GitHub MCP Server? - GitHub MCP Server is the official Model Context Protocol server from GitHub that provides AI agents with structured access to GitHub repositories, issues, pull requests, and code search through standardized MCP tool calls. - Is GitHub MCP Server free? - Yes, GitHub MCP Server is open-source under the MIT license. It is part of the official modelcontextprotocol/servers repository and can be self-hosted. - Which agents support GitHub MCP Server? - Any MCP-compatible agent host can use GitHub MCP Server, including Claude Desktop, OpenClaw, Cline, Continue.dev, and other MCP-enabled coding tools. - How do I install GitHub MCP Server? - Install via npx: npx @anthropic-ai/mcp-github. You must provide a GitHub personal access token. The server can also run via Docker or as a Node.js process. - Can GitHub MCP Server write to repositories? - Yes. The server supports creating issues, reviewing pull requests, and managing repository content. Permission level depends on the GitHub token scope you provide. ## What It Does GitHub MCP Server is a plugin in the plugins category. GitHub MCP Server is the official Model Context Protocol server from GitHub that lets AI agents browse repositories, create and manage issues, review pull requests, search code, and interact with GitHub's API through standardized MCP tool calls. ## How To Evaluate Evaluate GitHub MCP Server by starting from the official sources, checking its repo, docs, mcp interface surface, and running one narrow workflow before expanding scope. ## Why It Matters Agents that need to interact with GitHub currently must parse web UI or use the REST API directly. GitHub MCP Server gives agents a structured MCP interface to browse code, manage issues, and review PRs without scraping. ## Best For - Developers building coding agents that interact with GitHub - Teams using MCP-compatible agent hosts like Claude, OpenClaw, and Cline - Builders who need agent-driven code review and issue triage ## Not For - Teams without MCP-compatible agent infrastructure - Workflows that already use the GitHub CLI or REST API directly ## Fit Matrix - Coding agent workflow: strong. GitHub MCP Server has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning. Required check: Run a small repository change and inspect the diff, tests, and rollback path. - Connector or protocol layer: strong. GitHub MCP Server has multiple signals for connector or protocol layer, including matching tags, capabilities, category, or positioning. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs. - Local or private AI stack: partial. GitHub MCP Server has at least one signal for local or private ai stack, but should be checked against a real task before adoption. Required check: Verify hardware requirements, data path, storage, and whether all calls stay in your environment. - Memory or RAG workflow: partial. GitHub MCP Server has at least one signal for memory or rag workflow, but should be checked against a real task before adoption. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data. - Reusable skill workflow: partial. GitHub MCP Server has at least one signal for reusable skill workflow, but should be checked against a real task before adoption. Required check: Run one skill end to end and check whether it produces evidence or structured output. - Browser automation: weak. GitHub MCP Server is not primarily positioned for browser automation in the current metadata. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs. ## Evidence - verified: GitHub MCP Server is listed as open source. Source: License metadata: MIT - verified: GitHub MCP Server has a recorded GitHub repository: modelcontextprotocol/servers/tree/main/src/github. Source: Resource facts and GitHub source link. - inferred: GitHub MCP Server supports these recorded deployment modes: self hosted. Source: OpenAgent decision signal metadata. - inferred: GitHub MCP Server is tagged with plugin, mcp, protocol, connectors capabilities. Source: OpenAgent capability taxonomy. ## Missing Checks - Repository freshness has not been recorded. ## Next Actions - Inspect repository: https://github.com/modelcontextprotocol/servers/tree/main/src/github - Read setup docs: https://github.com/modelcontextprotocol/servers?tab=readme-ov-file#github ## Facts - Category: plugins - Resource type: plugin - Open source: yes - License: MIT - Last verified: 2026-06-24 - GitHub repo: modelcontextprotocol/servers/tree/main/src/github - GitHub stars: 32000 ## Capabilities - plugin - mcp - protocol - connectors ## Structured Use Case Tags - developer-workflow - self-hosted-ai ## Links - GitHub: https://github.com/modelcontextprotocol/servers/tree/main/src/github - Documentation: https://github.com/modelcontextprotocol/servers?tab=readme-ov-file#github ## Structured Outputs - JSON: https://www.openagent.bot/plugins/github-mcp-server.json - Markdown: https://www.openagent.bot/plugins/github-mcp-server.md - Agent JSON: https://www.openagent.bot/plugins/github-mcp-server.agent.json - Canonical: https://www.openagent.bot/plugins/github-mcp-server