MCP server
GitHub MCP server
GitHub's official MCP server lets AI read repositories, search code, manage issues and pull requests and, when allowed, change files.
- Official server
- Developer tools
At a glance
- Maintained by
- GitHub
- Tools exposed
- 10 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
GitHub is where most software teams keep their code, issues and reviews. GitHub's official MCP server lets an assistant read repositories and files, search code, list and write issues, open and read pull requests and, if allowed, create branches, commit files and merge.
For development teams, it connects a coding assistant to the real project instead of a pasted snippet. For managers, it makes questions like "which pull requests are waiting for review" a one-line request.
It replaces the older MCP reference server, which was archived. It offers a read-only mode, which we use for anything beyond hands-on coding. Tokens should be fine-grained and limited to the repositories a task needs. We never let an agent merge to a protected branch without a person approving the review.
Use cases
Best business use cases
Review help
Issue triage
Code search
Release notes
Status questions
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read and write: reads repos, issues and PRs, and can create issues, branches, files and merge PRs; a read-only mode is available.
-
get_meGet the signed-in user's profile.
-
search_repositoriesSearch repositories.
-
get_file_contentsGet file or directory contents.
-
search_codeSearch code across GitHub.
-
list_issuesList issues in a repository.
-
issue_writeCreate or update an issue.
-
create_pull_requestOpen a new pull request.
-
pull_request_readGet details for a single pull request.
-
merge_pull_requestMerge a pull request.
-
create_or_update_fileCreate or update a file in a repository.
Workflows
Example workflows
Weekly issue triage
-
1
The assistant lists new issues from the last week.
-
2
It summarizes each one and suggests labels.
-
3
It finds likely duplicates.
-
4
A maintainer reviews the suggestions.
-
5
Approved labels and links are applied.
Draft release notes
-
1
Ask for pull requests merged since the last release.
-
2
The assistant reads titles and descriptions.
-
3
It groups changes into features and fixes.
-
4
It drafts release notes in plain language.
-
5
A person edits and publishes them.
Prompts
Example prompts
“List open pull requests waiting more than three days for review, with authors.”
“Summarize this pull request and flag anything that touches payments code.”
“Draft release notes for everything merged since tag v2.4.0.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"github": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GITHUB_PERSONAL_ACCESS_TOKEN",
"ghcr.io/github/github-mcp-server"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_PAT"
}
}
}
}Claude Code: terminal
claude mcp add --transport http github https://api.githubcopilot.com/mcp -H "Authorization: Bearer YOUR_GITHUB_PAT"- Hosted server: streamable-http; https://api.githubcopilot.com/mcp/; OAuth (host must support it) or header Authorization: Bearer <GITHUB_PAT>.
- Local server: stdio; ghcr.io/github/github-mcp-server; github-mcp-server stdio (GitHub releases).
- Needs: GITHUB_PERSONAL_ACCESS_TOKEN (or OAuth login).
Security
Security considerations
-
Fine-grained tokens
Limit tokens to specific repositories and permissions.
-
Read-only mode
Use read-only mode unless the task needs to write.
-
Protected branches
Keep branch protection and required reviews on.
-
Untrusted text
Issue and PR text can contain misleading instructions. Review agent actions.
Related servers
Servers that pair well with it
GitLab
GitLab's built-in MCP server lets AI read projects, code, merge requests and pipelines and create commits and work items. In beta.
Git
The MCP project's Git reference server lets AI read history and diffs and stage, commit and switch branches in a local repository.
Sentry
Sentry's official MCP server lets AI search errors, events and traces, read issue details, get AI analysis and update issues.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- AI copilots AI helpers built into your product or internal tools that draft, summarize and suggest while people decide.
- MVP development A first version with just enough features to put in front of real users and learn what to build next.
- Internal tools Custom software for your own team: trackers, approval flows and back-office systems that replace spreadsheets.
- Business process automation Map a process that runs on email and spreadsheets and turn it into software with clear steps and owners.
- Legacy modernization Replace an aging system step by step, with the business running normally while the new parts take over.
Solutions
View all solutions- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- Approval workflows Requests, approvals and reminders in one place, with clear owners and deadlines instead of long email threads.
- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- Automated quoting Draft accurate quotes and proposals from a request, your price rules and past work, for a person to approve.
- AI-assisted content workflows Briefs, first drafts, edits and repurposing in a workflow where people set the angle and approve every word.
Industries
View all industriesGuides and articles
View all guides and articles- Where AI helps in development, and where it does not An honest map of the development tasks AI speeds up and the ones that still need experienced people.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
- What is AI-accelerated development? How software teams use AI to plan, code, test and document faster, and where people still make every decision.
- What are AI agents and how do businesses use them? What AI agents are, real business uses, the controls they need and how to start with one safely.
- AI chatbot vs AI agent What separates a chatbot that answers from an agent that acts, and when you need each.
AI models
View all ai models- Mistral Medium 3.5 A newer open-weight Mistral model for agent and coding work, with image input, tool calling, structured outputs and a 256K window.
- Codestral 25.08 Mistral's low-latency coding model for code completion and generation, with fill-in-the-middle support, tool calling and a 128K window.
- Qwen3-Coder Qwen's open-weight coding models under Apache 2.0, from the efficient Qwen3-Coder-Next to the large 480B model, with tool use and long context.
- Coding Models that write, review and explain code, and power coding assistants and developer tools.
- Claude Opus 5.5 Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
- GPT-6 Sol The middle model of the GPT-6 family, positioned for complex coding and agentic workflows at a mid price level.
Glossary terms
View all glossary terms- AI copilot An AI copilot is an assistant built into a tool people already use, which suggests, drafts and explains while the person stays in control.
- AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
- Claude Code Claude Code is Anthropic's agentic coding tool, which works in a developer's terminal, IDE, desktop app or browser to read code, run commands and make changes.
- Automation Automation is using software to perform a task or process with little or no human effort each time it runs.
- Chatbot A chatbot is software that holds a conversation with people through text or voice, answering questions or completing simple tasks.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It is maintained by GitHub and replaces the archived reference server.
Yes. A read-only mode is available.
It has a merge tool. Keep branch protection and human review in place.