GitHub MCP Server — 44 AI Tools | Claude, ChatGPT & More

GitHub MCP ServerGitHub MCP server with 44 ready-to-use AI tools. Connect GitHub to Claude, ChatGPT, Gemini, or any MCP-compatible AI assistant. Cloud MCP connector — no install, no Docker, works from any browser.Category: Developer Tools. 44 tools available. Authentication: API Key.Let your AI manage GitHub for youWhy GitHub + AI?You juggle dozens of repos, PRs, and issues every day. Switching tabs between your AI assistant and GitHub to check statuses, review diffs, and triage issues is a constant time sink. Just ask your AI directly.Example prompts you can send your AI about GitHub

Ask: "Show all open PRs that need my review across all repos"
AI does: AI searches your repositories for pull requests awaiting your review, sorted by age, with summary of changes.

Ask: "Create an issue in my-app: "Fix dark mode toggle on mobile""
AI does: AI creates the issue with a proper title, adds labels, and returns the issue URL ready to share.

Ask: "What failed in the latest CI run for our deploy branch?"
AI does: AI fetches workflow runs, finds the failed one, lists the failing jobs, and shows the error output.

Ask: "Summarize the changes in PR #42"
AI does: AI pulls the PR diff, lists modified files, and generates a human-readable summary of what changed and why.

Featured GitHub Tools

list-pull-requests: List pull requests in a GitHub repository with optional filters for state, branch, and sort order. Returns PR number, title, state, author, head/base branches, labels, reviewers, draft status, and dates. FILTERING: Use state to filter open/closed/all, head to filter by source branch, base to filter by target branch. EXAMPLES: "Show open PRs" → owner="myuser", repo="my-repo", state="open" "PRs targeting main" → owner="myuser", repo="my-repo", base="main" "All PRs from the feature branch" → owner="myuser", repo="my-repo", head="myuser:feature/login" "Most discussed PRs" → owner="myuser", repo="my-repo", sort="popularity" WHEN TO USE: User asks to list, show, or browse pull requests, or wants to see what's pending review.

search-issues: Search for issues and pull requests across GitHub using keywords and filters. Returns matching issues/PRs with title, state, repo, author, labels, and comments count. The query uses GitHub's issue search syntax for powerful filtering. QUERY EXAMPLES: • In a specific repo: query="bug is:issue is:open repo:facebook/react" • By label: query="label:bug label:high-priority repo:myuser/myapp" • Assigned to someone: query="assignee:octocat is:open" • PRs only: query="is:pr is:open review:required repo:myuser/myapp" • Mentions me: query="mentions:myusername is:issue" WHEN TO USE: User asks to search issues, find bugs, search across repos, or "find issues about X".

create-issue: Create a new issue in a GitHub repository. Returns the created issue number, URL, and full details. Only the title is required — body, labels, assignees, and milestone are optional. The body supports full GitHub-flavored Markdown (headings, code blocks, task lists, mentions, etc.). EXAMPLES: "Create a bug report for the login page" → owner="myuser", repo="my-repo", title="Login page returns 500 error", body="Steps to reproduce:...", labels=["bug"] "Add a feature request" → owner="myuser", repo="my-repo", title="Add dark mode support", labels=["enhancement"] "Create an issue and assign it to john" → owner="myuser", repo="my-repo", title="Fix header", assignees=["john"] WHEN TO USE: User asks to create, open, file, or report an issue, bug, feature request, or task.

get-pull-request-diff: Get the raw diff (unified diff format) of all changes in a pull request. Returns the full text diff showing exactly what lines were added (+) and removed (-) in every changed file. Use this for code review or to understand exactly what a PR changes. For a summary of changed files without the full diff, use list-pull-request-files instead. EXAMPLES: "Show me the diff for PR #42" → owner="myuser", repo="my-repo", pullNumber=42 "What exactly changed in PR #10?" → owner="myuser", repo="my-repo", pullNumber=10 WHEN TO USE: User asks to see the diff, code changes, or wants to review the exact changes in a PR.

list-workflow-runs: List recent workflow run executions for a repository or a specific workflow. Returns run ID, status (queued/in_progress/completed), conclusion (success/failure/cancelled), triggering event, branch, commit SHA, actor, and timestamps. FILTERING: Narrow by workflow (workflowId), branch, event type, or status. EXAMPLES: "Show recent CI runs" → owner="myuser", repo="my-repo" "Show runs for the test workflow" → owner="myuser", repo="my-repo", workflowId="test.yml" "Failed runs on main" → owner="myuser", repo="my-repo", branch="main", status="completed" (then check conclusion) WHEN TO USE: User asks about CI status, build history, workflow runs, deployment status, or "is the build passing?".

get-file-contents: Read the contents of a file or list the entries in a directory from a GitHub repository. For files: returns the decoded text content, file size, and SHA. For directories: returns a list of file/directory names with their types and sizes. You can optionally read from a specific branch or commit by passing the "ref" parameter. NOTE: Files larger than 1MB may be truncated. For very large files, use the Git Blobs API instead. EXAMPLES: "Show me the README" → owner="myuser", repo="my-repo", path="README.md" "What files are in the src folder?" → owner="myuser", repo="my-repo", path="src" "Show package.json from the develop branch" → owner="myuser", repo="my-repo", path="package.json", ref="develop" WHEN TO USE: User asks to read, view, show, or display a file or directory from a GitHub repo.

Frequently Asked Questions about GitHubCan my AI create pull requests and merge them on GitHub?Yes. The GitHub integration includes tools for creating pull requests, commenting, requesting reviewers, and merging — subject to your GitHub permissions. Your AI can open a PR from a branch, write the description, and merge once checks pass, all from a single conversation.Does the GitHub connector support private repositories?Yes. When you create your GitHub Personal Access Token (classic or fine-grained), grant the repo scope for private repo access. The token is encrypted in our database and only decrypted in memory during tool calls — we never log the response bodies.How is this different from the official GitHub MCP server?GitHub's first-party MCP server is designed for local use (Claude Desktop, IDEs). LearnToSpeak.ai runs it in the cloud so it works from claude.ai and chatgpt.com directly — no local install, and you can use it from any device. If you already use Claude Desktop or an IDE with MCP support, the official server is fine too.What happens if my GitHub token expires or I rotate it?Paste the new token in the LearnToSpeak.ai dashboard — it takes effect on the next AI request. Revocation is instant: remove the token and the AI immediately loses access. For long-term use, we recommend fine-grained tokens scoped to specific repositories with the minimum required permissions.How do I connect GitHub to Claude or ChatGPT?Create a free LearnToSpeak.ai account, add your GitHub credentials in the dashboard, and paste the generated OAuth URL into Claude.ai's custom connectors or ChatGPT's developer apps. The integration runs fully in the cloud — no desktop app, no CLI, no local install.Does it cost anything to connect GitHub?The GitHub integration is free during the LearnToSpeak.ai public beta. You only need a paid plan from Anthropic or OpenAI (Claude Pro/Max/Team or ChatGPT Plus/Pro/Team) since custom connectors require it on the AI provider side.Which AI assistants support the GitHub connector?Claude.ai (Pro, Max, Team, Enterprise) and ChatGPT (Plus, Pro, Team) both support the GitHub integration via the MCP (Model Context Protocol) standard. The same credentials work across both platforms — add the connector once, use it everywhere.How many GitHub tools does my AI get access to?Your AI gets 44 ready-to-use tools for GitHub, covering the most common read and write operations. Each tool is a discrete action the AI can call on demand — no multi-step prompting, no screen scraping, no workarounds.Is it safe to give an AI access to my GitHub account?Yes. Your GitHub credentials are encrypted at rest with AES-256-GCM and only decrypted in memory when the AI makes a request. LearnToSpeak.ai uses OAuth 2.1 with mandatory PKCE for the AI-to-platform connection, and you can revoke access instantly from the dashboard. We never store or log the actual tool responses returned to the AI.Why use LearnToSpeak.ai instead of running an MCP server locally?Cloud MCP servers work from any browser on any device — no Node.js install, no Docker, no local ports, no maintenance. Configure GitHub once in the dashboard and your AI connects from claude.ai or chat.openai.com directly. That's the entire value proposition: web AI assistants don't read your filesystem, they read our servers.What is the GitHub MCP server?The GitHub MCP server is a cloud-hosted integration that gives AI assistants direct access to GitHub through 44 tools via the Model Context Protocol (MCP) standard. It works with Claude, ChatGPT, Gemini, and any MCP-compatible AI — no local installation or Docker required.How do I connect GitHub to Claude via MCP?Sign up at LearnToSpeak.ai, add your GitHub credentials, and copy the generated MCP URL into Claude.ai's custom connectors (Settings → Developer → Custom Connectors). The cloud MCP server handles the connection — no CLI, no local server, no Docker.How do I connect GitHub to ChatGPT via MCP?Sign up at LearnToSpeak.ai, add your GitHub credentials, and copy the generated MCP URL into ChatGPT's developer apps (Settings → Apps → Advanced → Developer mode). Works with any ChatGPT Plus, Pro, or Team account.What can AI do with GitHub through MCP?GitHub offers 44 MCP tools covering Manage repositories, issues, pull requests, workflows, and collaborate on code. Ask your AI to perform any of these actions in natural language — it calls the right tool automatically.What is MCP (Model Context Protocol)?MCP is an open standard that lets AI assistants like Claude, ChatGPT, and Gemini connect directly to external apps and services. LearnToSpeak.ai hosts cloud MCP servers so you don't need to install anything locally — your AI connects from any browser.Related MCP Servers

GitLab MCP Server — 90 tools

NetBox MCP Server — 179 tools

Cisco CPNR MCP Server — 36 tools

Grafana MCP Server — 50 tools

Graylog MCP Server — 12 tools

Browse all 34 MCP servers