Back
Marketplace/GitHub

TL;DR

GitHub is a Version Control MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent official GitHub MCP — repos, issues, PRs. Install in 1 minute with mcpizy install github.

🐙

GitHub

Verified 9 tools Supports hosted execution →

Version Control

Last updated May 30, 2026 · By MCPizy team

Official GitHub MCP — repos, issues, PRs

Official homepage

Run GitHub without any local install

Connect your GitHub account once — MCPizy stores the credentials encrypted and uses them whenever you run a recipe in managed mode.

Checking connection…

Install GitHub

Via MCPizy CLI (recommended):
mcpizy install github
Or run directly:
npx -y @modelcontextprotocol/server-github
View on GitHub

Tools exposed

9 tools available
get_repository

Get details about a GitHub repository

Inputs

  • ownerstringrequired
  • repostringrequired
list_issues

List issues in a repository with filters

Inputs

  • ownerstringrequired
  • repostringrequired
  • statestringoptional
create_issue

Open a new issue with a title and body

Inputs

  • ownerstringrequired
  • repostringrequired
  • titlestringrequired
  • bodystringoptional
list_pull_requests

List pull requests in a repository

Inputs

  • ownerstringrequired
  • repostringrequired
  • statestringoptional
create_pull_request

Open a new pull request between two branches

Inputs

  • ownerstringrequired
  • repostringrequired
  • titlestringrequired
  • headstringrequired
  • basestringrequired
get_file_contents

Read a file from a repo at a given ref

Inputs

  • ownerstringrequired
  • repostringrequired
  • pathstringrequired
create_or_update_file

Write a file to a repo (for commits via the API)

Inputs

  • ownerstringrequired
  • repostringrequired
  • pathstringrequired
  • contentstringrequired
  • messagestringrequired
search_code

Search code across GitHub

Inputs

  • qstringrequired
search_repositories

Search GitHub repositories

Inputs

  • querystringrequired

Configuration

Works identically across clients. Only the config file path differs.

Claude Code~/.claude.json
{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-github"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_..."
      }
    }
  }
}
Cursor.cursor/mcp.json
{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-github"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_..."
      }
    }
  }
}
Windsurf~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-github"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_..."
      }
    }
  }
}

Authentication setup

  1. 1

    Create a fine-grained personal access token with repo + issues scopes

    Get it GITHUB_PERSONAL_ACCESS_TOKEN

What you can do with GitHub MCP

Paste any of these prompts into Claude Code, Cursor or another MCP-compatible client.

“Show me all open issues in `vercel/next.js` tagged `bug` from the last week”

Uses: list_issues

“Open an issue in my repo titled 'Fix CI flakiness' with a description of the problem”

Uses: create_issue

“Read the README of `anthropics/claude-code` and summarise the quickstart”

Uses: get_file_contents

“Find TypeScript repos with more than 10k stars that mention 'MCP server'”

Uses: search_repositories

“Create a PR from my branch `feat/auth` into `main` with title 'Add OAuth flow'”

Uses: create_pull_request

Why GitHub MCP matters

GitHub MCP is the most installed MCP server in the wild — and for good reason. It exposes the GitHub API as a clean set of agent tools: read repos, list and create issues, manage PRs, search code, write files. For any AI coding workflow, having Claude or Cursor call GitHub directly (instead of you copy-pasting issue text) compresses 10-minute tasks into 30 seconds.

Where it shines: PR review automation. The agent reads `list_pull_requests`, fetches the diff, leaves contextual `create_comment` calls. Issue triage is the second-best use: "look at the 20 oldest open issues, group by area, suggest labels." The official server (run by the Anthropic / Model Context Protocol team) ships ~9 tools that cover 90 % of the daily GitHub surface. There's also a more aggressive community fork with full Actions / projects / packages support if you need deeper workflows.

Compared to Linear MCP for issue work, GitHub wins when your team lives in GitHub-native projects and PR comments are the source of truth. Linear wins for sprint/cycle workflows and richer issue states. We run both — GitHub MCP for code/PRs, Linear MCP for planning. Token cost is lean for read tools (issues, PRs are short), heavier for `get_file_contents` on large files (one 1k-line file ≈ 4k tokens). Authentication is a fine-grained PAT — set the smallest scope (read-only repo + issues for safety), upgrade to write only when you have explicit human approval in the loop.

Common pitfalls

Fine-grained tokens have surprising scope limits — the "all repositories" toggle does NOT include private repos by default. If `list_pull_requests` returns empty for a private repo, regenerate the token with that repo explicitly selected.

`search_code` uses GitHub's code search index, which is eventually consistent and lossy. Recently pushed code can take 5-30 min to appear; some file types (lock files, vendored deps) are not indexed at all. For "find all callers of X" the agent should fall back to cloning + grep when search returns < 3 hits.

`create_or_update_file` commits via the API, which means no GPG signing, no pre-commit hooks, and no CI run on the same commit unless your branch protection allows it. For anything more than docs / small fixes, ask the agent to push to a branch and open a PR — never to commit directly to main.

Rate limits: 5,000 req/h for authenticated PAT. An aggressive triage of 200 issues at 5 calls each = 1,000 req — fine. A repo-wide audit across 50 repos can hit the wall. The agent should batch via GraphQL or accept paginated reads.

How GitHub MCP compares

Honest pros/cons against the closest version control MCP servers.

ServerStrengthsTrade-offs
GitLab MCPSame primitives if your team is on GitLab, MIT-licensedSmaller community, fewer tools maintained, no GraphQL coverage yet
Gitea MCPSelf-hostable, lightweight, good for private dev orgsTools cover only basic repo/issue ops, no PR automation depth
Linear MCPBetter for sprint/cycle planning, cleaner issue statesNo code-side primitives — you still need GitHub for PRs

Works with

Claude Code
Claude Desktop
Cursor
Windsurf
VS Code + Copilot
Any MCP Client

More Version Control MCPs

🍵

Gitea

Manage Gitea repositories, issues, and pull requests for self-hosted Git from AI agents.

🦊

GitLab

GitLab API — projects, merge requests, pipelines

Alternatives to GitHub

If GitHub doesn't fit your stack, these Version Control MCP servers solve similar problems.

📦

Git

Local Git repository operations

🔴

Gitee

Gitee API integration for repository, issue, and pull request management. China's GitHub.

🐙

GitKraken

CLI for interacting with GitKraken APIs including Jira, GitHub, GitLab, and Bitbucket.

Key Takeaways

  • GitHub exposes 9 tools for version control workflows in Claude Code, Cursor and Windsurf.
  • Authentication: 1 step (GITHUB_PERSONAL_ACCESS_TOKEN).
  • Install in 1 command: mcpizy install github — config written to your client automatically.
  • Free and open source (GitHub source linked above) — verified compatible with every MCP client (Claude Code, Claude Desktop, Cursor, Windsurf, VS Code + Copilot).
  • Best use case: "Show me all open issues in `vercel/next.js` tagged `bug` from the last week".

Frequently asked questions

What is the GitHub MCP server?

The GitHub MCP server is an Version Control Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents official GitHub MCP — repos, issues, PRs. It exposes GitHub's capabilities as tools the AI can call directly from your editor or CLI.

How do I install GitHub MCP with Claude Code?

The fastest way is the MCPizy CLI: run `mcpizy install github` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @modelcontextprotocol/server-github` and restarting Claude Code.

Is GitHub MCP free?

Yes. The GitHub MCP server is free and open source (see the GitHub repository linked on this page). You may still need a GitHub account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.

Does GitHub MCP work with Cursor and Windsurf?

Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.

What can I do with GitHub MCP?

Once installed, your AI agent can official GitHub MCP — repos, issues, PRs directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run GitHub operations, inspect results, chain GitHub with other MCP servers (see our Workflow Recipes), and automate repetitive version control tasks without leaving your editor.

Manage all your MCPs in one place

Monitor usage, track costs, and discover new MCPs.

Get Started Free