Provides GitHub API access for repositories, issues, pull requests, reviews, and code search. Agents can summarize PR diffs, draft code reviews, manage issues, and navigate large organizations using OAuth-authenticated API calls. Supports both github.com and GitHub Enterprise deployments.
Use cases
- Reviewer agent analyzes PR changes and drafts constructive code review comments
- Project manager agent creates and triages issues based on conversation context
- Developer agent searches codebase across organization repositories for patterns
- Release engineer agent generates changelog by analyzing merged PRs since last release
- Onboarding agent explores repository structure to understand a new codebase
Key features
- Cursor
- Codex
- Claude Desktop
Frequently Asked Questions
- What GitHub scopes does the MCP server require?
- The server requires repository and read-only organization scopes. For full functionality including issues and PRs, grant repo, read:org, and read:discussion scopes.
- Does it support GitHub Enterprise Server?
- Yes, you can configure the server to use your GitHub Enterprise instance URL instead of github.com by setting the GITHUB_API_URL environment variable.
- How does the agent handle rate limits?
- The server implements exponential backoff for rate limit responses. For heavy usage, consider authenticating with a GitHub App installation instead of personal access tokens.
Related
Related
3 Indexed items
Semgrep MCP
Connects AI coding agents to Semgrep static analysis rules and findings so security reviews can start from actual scan results. Agents can look up rule definitions, triage findings, and verify fixes without pasting SARIF outputs. Integrates with CI/CD pipelines.
Cloudflare MCP
Bridges AI agents to Cloudflare Workers, KV storage, R2 object storage, and D1 databases for edge deployment inspection and management. Agents can check Workers status, inspect KV namespaces, query D1 databases, and monitor R2 buckets directly from the coding environment.
GitLab MCP
Integrates GitLab projects, merge requests, CI/CD pipelines, and group metadata into AI assistants. Agents can review MR diffs alongside code, inspect pipeline failures, and track approval status without leaving the IDE. Supports gitlab.com and self-hosted GitLab instances.