About GitHub MCP Server in Go
An unofficial GitHub MCP server implemented in Go, for AI assistants that work with repositories, branches, files, issues, and code through the GitHub API. Its tools cover search, reading, and writing, with token authentication via environment variables or HTTP headers.
Key features
- 01Search repositories, code, issues, and users
- 02Create repositories, forks, and branches
- 03Read, create, or update files
- 04Push multiple files in one commit
- 05Create, inspect, and update issues
Use cases
- 01Search GitHub repositories and code
- 02Create branches and update repository files
- 03Review and maintain issues and comments
MCP support
It exposes GitHub API operations to AI assistants as MCP tools. GitHub tokens can be supplied through an environment variable or HTTP request headers.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEGitHub MCP Server in Go
A Go implementation of the GitHub Model Context Protocol (MCP) server. This implementation allows AI assistants to interact with the GitHub API to perform operations such as creating repositories, managing branches, manipulating files, and more.
Prerequisites
- Go 1.21 or higher
- A GitHub personal access token with appropriate permissions
Installation
go get github.com/metoro-io/github-mcp-server-go
Authentication
The server supports two methods of authentication:
Environment Variable Authentication
Set your GitHub personal access token as an environment variable:
export GITHUB_PERSONAL_ACCESS_TOKEN=your_github_token
HTTP Header Authentication
The server can also extract authentication tokens from HTTP requests. You can pass your GitHub token via the Authorization header:
Authorization: Bearer your_github_token
or simply:
Authorization: your_github_token
Context Passthrough
For HTTP handlers, the server supports both:
- The standard
http_requestcontext value for HTTP requests. - The
ginContextvalue when using the Gin framework.
This enables seamless integration with different web frameworks while maintaining a consistent authentication mechanism.
Usage
-
Set your GitHub personal access token (as described in the Authentication section).
-
Run the server:
go run main.go
Available Tools
The server provides the following tools:
- search_repositories: Search for GitHub repositories
- create_repository: Create a new GitHub repository in your account
- fork_repository: Fork a GitHub repository to your account or specified organization
- create_branch: Create a new branch in a GitHub repository
- get_file_contents: Get the contents of a file or directory from a GitHub repository
- create_or_update_file: Create or update a single file in a GitHub repository
- push_files: Push multiple files to a GitHub repository in a single commit
- create_issue: Create a new issue in a GitHub repository
- get_issue: Get details of a specific issue in a GitHub repository
- list_issues: List issues in a GitHub repository with filtering options
- update_issue: Update an existing issue in a GitHub repository
- add_issue_comment: Add a comment to an existing issue
- list_commits: Get list of commits of a branch in a GitHub repository
- search_code: Search for code across GitHub repositories
- search_issues: Search for issues and pull requests across GitHub repositories
- search_users: Search for users on GitHub
Development
Project Structure
main.go: Entry point for the applicationcommon/: Common utilities and error handlingoperations/: GitHub API operations implementationtools/: MCP tool definitions and handlers
Building from Source
go build -o github-mcp-server
Running Tests
go test ./...
License
This project is licensed under the MIT License.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.