# GitHub MCP MCP > GitHub MCP connects your AI agent directly to the world's largest developer platform. You manage repositories, track issues, and search code without ever leaving your chat interface. Instantly list repos across organizations, check file contents in any project folder, or open new issues—all through natural conversation. ## Overview - **Category:** industry-titans - **Price:** Free - **Tags:** version-control, repository-management, pull-requests, issue-tracking, code-search ## Description Need to keep up with complex codebases? This MCP gives your AI agent direct access to GitHub's entire ecosystem. Forget switching tabs and manually digging into dashboards just to figure out who changed what or why a feature request stalled. You can ask your agent to list all repositories for a specific organization, grab the full contents of a README file, or even track down every commit made in the last week. It’s about getting answers fast. Instead of navigating through dozens of menus, you just talk to your AI client. Want to see if a pull request is ready to merge? Ask. Need to open a new bug report and tag three people? Tell it to do it. This capability makes GitHub's massive data set actionable right where you work. It’s available via the Vinkius Marketplace, giving any MCP-compatible client deep, structured access to your development history. ## Tools ### add_issue_comment Adds a comment to an existing issue or pull request using standard markdown formatting. ### create_new_issue Opens a brand new, structured bug report or feature request within a repository. ### create_pull_request Generates and submits a pull request between two specific branches in a repository. ### get_file_contents Reads and returns the full text content of any specified file or directory within a project. ### get_issue_details Retrieves all specific information about one issue, given its unique number. ### get_my_github_profile Returns detailed identity and permission context for the connected user account. ### get_repository_details Retrieves essential metadata, like name and visibility, for a single specified repository. ### list_branches Lists all active branches associated with a given repository. ### list_commits Shows recent changes to the code, optionally filtering by branch name or SHA hash. ### list_org_repositories Retrieves a list of all repositories belonging to an organization account. ### list_pull_requests Gathers a summary list of current and past pull requests for a project. ### list_releases Fetches information about all official releases tagged within the repository's history. ### list_repo_issues Retrieves a list of open and closed issues belonging to a specific repository. ### list_stargazers Lists the users who have starred the repository, useful for community engagement metrics. ### list_user_repositories Retrieves a list of all repositories owned by the connected user account. ### search_github_code Executes a targeted search across code snippets within your codebase for specific keywords or patterns. ### search_github_repositories Searches all available repositories by name or keyword, regardless of ownership. ### verify_api_connection Checks the connection status to ensure your authentication token is valid and active. ## Prompt Examples **Prompt:** ``` List the last 5 open issues in the 'facebook/react' repository. ``` **Response:** ``` Retrieving issues... I found 5 recent open issues in react, including 'Bug: Hydration error' and 'Feature request: New hook'. Would you like the details for any of them? ``` **Prompt:** ``` Find all repositories for the organization 'vinkius'. ``` **Response:** ``` Searching organization... I found 12 repositories for Vinkius, including 'vurb-core' and 'mcp-originals'. Would you like to see the stars count for these? ``` **Prompt:** ``` Read the content of the 'README.md' file in 'vinkius/vurb-docs'. ``` **Response:** ``` Fetching file... The README.md for vurb-docs contains: '# Vurb Documentation - Welcome to the official guide...'. Would you like me to summarize the installation steps? ``` ## Capabilities ### Discovering Project Structure You can list all repositories for a user or organization and get metadata on specific projects to understand the overall scope. ### Handling Collaborative Tasks The agent lets you open new issues, add comments to existing tickets, and create pull requests directly from your conversation. ### Analyzing Codebase Details You can retrieve the full contents of specific files or directories across any repository, allowing deep code context for analysis. ### Reviewing Project History The MCP lets you list recent commits and track all open issues and pull requests to monitor project activity. ### Searching Code and Repositories You can perform powerful searches across GitHub's database to isolate specific code snippets or find relevant repositories by name. ## Use Cases ### The PM needs project visibility. A Project Manager has been asked for an update on a feature rollout. Instead of manually navigating to the repo's issues page, they ask their agent to 'list all open issues in vinkius/vurb-docs.' The MCP uses `list_repo_issues` and summarizes which tickets are stalled or waiting for review. ### The Dev needs historical context. A developer is debugging a tricky bug. Instead of searching through dozens of commits, they ask the agent to 'list commits in the main branch from last week.' The MCP uses `list_commits` and provides the commit hashes and summaries needed for immediate diagnosis. ### The DevOps team needs an audit trail. An engineer needs to verify that a specific piece of code used in a release is documented correctly. They ask the agent to 'get file contents for README.md' and instantly retrieve the source text, confirming compliance. ### The Team Lead needs project coordination. A team lead needs to report on all available code assets across departments. They prompt the agent to find 'all repositories belonging to our company organization,' using `list_org_repositories` for a complete inventory. ## Benefits - Instantly see the status of every project. You can use `list_org_repositories` to list all projects owned by an organization in one go, instead of visiting multiple dashboard tabs. - Keep track of development progress with minimal effort. Use `list_pull_requests` and `get_issue_details` so your agent can summarize the current state of a feature request before you even open it. - Deep code context is now available to your AI client. The `get_file_contents` tool lets you pull the exact text from any file, giving your agent enough data to answer complex questions about logic or structure. - Streamline bug tracking by opening tickets on demand. You can use `create_new_issue` and follow up immediately with `add_issue_comment`, all without logging into a separate ticketing system. - Search the code instantly, no GUI required. When you need to find a specific function or pattern across multiple files, rely on `search_github_code` instead of manual keyword searches. ## How It Works The bottom line is: you authorize your AI client once, then it handles complex GitHub workflows via simple conversation prompts. 1. First, subscribe to this MCP via the Vinkius Marketplace and provide your GitHub Personal Access Token. 2. Next, connect that token to any compatible AI client. This authorizes your agent to read and write data on your behalf. 3. Finally, start by telling your agent what you need—for example, 'List all open issues for Project X'—and the tool executes the request. ## Frequently Asked Questions **How do I list all my company's projects using the list_org_repositories tool?** The agent uses `list_org_repositories` to gather a complete inventory of every repository under your organization. This is faster than navigating through individual team dashboards. **What does add_issue_comment do in the GitHub MCP?** `add_issue_comment` allows you to reply directly to an existing issue or PR from your chat, adding context and updates without leaving the agent interface. **Can I find code snippets using search_github_code?** Yes. `search_github_code` lets you run powerful searches across the entire repository's codebase to isolate specific functions or patterns, much faster than a simple keyword search. **How do I know if my API connection is working with verify_api_connection?** Simply ask your agent to run `verify_api_connection`. The tool checks the authentication token and confirms that your MCP client has active, valid access rights to GitHub. **What if I need more info about a specific bug? Should I use get_issue_details?** Yes. `get_issue_details` pulls all the deep metadata for one issue—the full conversation history, labels, and assignees—giving you the complete picture in one call. **If I want to track a feature or fix, how do I use the `create_pull_request` tool?** You must specify both the head branch (your changes) and the base branch (the target merge location). This action initiates the formal pull request process so your agent can monitor its status and lifecycle. **When I use `get_file_contents` to read a file, what kind of data does it give me?** It returns the raw text content of the specified file. You get pure code or documentation text, which you can then pass directly to your agent for analysis, summarization, or modification. **How do I know what my current permissions are on GitHub? Should I use `get_my_github_profile`?** Yes. Calling `get_my_github_profile` provides detailed information about the authenticated user's identity and associated account context. Your agent uses this to confirm your access rights before attempting major actions.