A Model Context Protocol (MCP) server built in TypeScript that integrates with GitHub's API, enabling AI assistants to manage repositories, issues
A Model Context Protocol (MCP) server built in TypeScript that integrates with GitHub's API, enabling AI assistants to manage repositories, issues, pull requests
A Model Context Protocol (MCP) server that provides tools for interacting with the GitHub API. This server allows LLM agents manage GitHub repositories, issues, pull requests, branches, files, and releases through a standardized interface.
github-mcp-server implements the Model Context Protocol (MCP), enabling standardized communication between LLMs and external systems through:
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| get_repository | Get detailed information about a specific repository Parameters: owner, repo |
| list_repositories | List repositories for the authenticated user Parameters: type (optional), sort (optional) |
| create_repository | Create a new GitHub repository Parameters: name, description (optional), private (optional) |
| list_branches | List branches in a repository Parameters: owner, repo, protected (optional), per_page (optional) |
| create_branch | Create a new branch Parameters: owner, repo, branch, sha |
| delete_branch | Delete a branch Parameters: owner, repo, branch |
| create_issue | Create a new issue in a repository Parameters: owner, repo, title, body (optional), labels (optional) |
| list_issues | List issues in a repository Parameters: owner, repo, state (optional), labels (optional) |
| create_pull_request | Create a new pull request Parameters: owner, repo, title, head, base, body (optional) |
| merge_pull_request | Merge a pull request Parameters: owner, repo, pull_number, commit_title (optional), commit_message (optional), merge_method (optional) |
| update_pull_request | Update an existing pull request Parameters: owner, repo, pull_number, title (optional), body (optional), state (optional), base (optional), maintainer_can_modify (optional) |
| list_pull_requests | List pull requests in a repository Parameters: owner, repo, state (optional), head (optional), base (optional), sort (optional), direction (optional) |
| update_file | Create or update a file in a repository Parameters: owner, repo, path, message, content, sha (optional), branch (optional) |
| create_release | Create a new release Parameters: owner, repo, tag_name, name (optional), body (optional), draft (optional), prerelease (optional) |
{
"mcpServers": {
"github": {
"command": "node",
"args": ["/path/to/github-mcp-server/build/index.js"],
"env": {
"GITHUB_TOKEN": "your_github_personal_access_token",
"LOG_LEVEL": "info",
"SERVER_NAME": "github-mcp-server"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| GITHUB_TOKEN | Credential the server authenticates with. | Yes |
| LOG_LEVEL | Configuration value read at startup. | Optional |
| SERVER_NAME | Configuration value read at startup. | Optional |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Automate registering functions in a python package as MCP tools.
MCP API Connect lets an assistant work with REST APIs through a locally installed MCP integration and supplied API documentation.
Age your receivables into 0-30, 31-60, 61-90 and over 90 day buckets by due date.
MCP server for StressZero Intelligence API — Burnout risk scoring for AI agents, coaches, and HR platforms