Enables comprehensive management of Forgejo repositories including issue tracking, project organization with labels and milestones, release management, pull request viewing, and Wiki page management.
Provides full repository management capabilities for Gitea instances including issue creation and editing, label and milestone management, release handling, pull request access, and Wiki administration.
Gitea/Forgejo MCP Server
Turn AI into your code repository management assistant
A Model Context Protocol (MCP) server that enables you to manage Gitea/Forgejo repositories through AI assistants like Claude, Gemini, and Copilot.
🚀 Why Use Forgejo MCP Server?
If you want to:
- Smart progress tracking: Let AI help you track project progress and analyze bottlenecks
- Automated issue categorization: Automatically tag issue labels and set milestones based on content
- Priority sorting: Let AI analyze issue content to help prioritize tasks
- Code review assistance: Get AI suggestions and insights in Pull Requests
- Project documentation organization: Automatically organize Wiki documents and release notes
Then this tool is made for you!
✨ Supported Features
Issue Management
- Create, edit, and view issues
- Add, remove, and replace labels
- Manage issue comments and attachments
- Set issue dependencies
Project Organization
- Manage labels (create, edit, delete)
- Manage milestones (create, edit, delete)
- Repository search and listing
Release Management
- Manage version releases
- Upload and manage release attachments
Other Features
- View Pull Requests
- Manage Wiki pages
- View Forgejo/Gitea Actions tasks
📦 Installation
Method 1: Use docker (Recommended)
For STDIO mode, you can skip to Usage section.
For SSE/Streamable HTTP mode, you should run forgejo-mcp
as server before configuring your MCP client.
Method 2: Install from source
Method 3: Download Pre-compiled Binaries
Download the appropriate version for your operating system from the Releases page.
🖥️ Usage
This tool provides two primary modes of operation: stdio
for local integration and http
for remote access.
Before actually setup you MCP client, you have to create an access token on the Forgejo/Gitea server.
- Log in to your Forgejo/Gitea instance
- Go to Settings → Applications → Access Tokens
- Click Generate New Token
- Select appropriate permission scopes (recommend at least
repository
andissue
write permissions) - Copy the generated token
💡 Tip: For security, consider setting environment variables instead of using tokens directly in config:
Stdio Mode (for Local Clients)
This is the recommended mode for integrating with local AI assistant clients like Claude Desktop or Gemini CLI. It uses standard input/output for direct communication.
Configure Your AI Client
Using docker:
Installed from source or pre-built binary:
You might want to take a look at Security Recommendations section for best practice.
HTTP Server Mode (for Remote Access)
This mode starts a web server, allowing remote clients to connect via HTTP. It's ideal for web-based services or setting up a central gateway for multiple users.
Run the following command to start the server:
The server supports two operational modes:
- Single-user mode: If you provide a
--token
(or environment variableFORGEJOMCP_TOKEN
) at startup, all operations will use that token. - Multi-user mode: If no token is provided, the server requires clients to send an
Authorization: Bearer <token>
header with each request, allowing it to serve multiple users securely.
Client Configuration
For clients that support connecting to a remote MCP server via HTTP, you can add a configuration like this. This example shows how to connect to a server running in multi-user mode:
or http
type (for Streamable HTTP, use different path in URL)
If connecting to a server in single-user mode, you can omit the headers
field.
🛡️ Security Recommendations
- Use environment variables: Set
FORGEJOMCP_SERVER
andFORGEJOMCP_TOKEN
, then remove--server
and--token
from your configuration - Limit token permissions: Only grant necessary permission scopes
- Rotate tokens regularly: Update access tokens periodically
📋 Usage Examples
After configuration, you can use natural language in your AI assistant to manage your repositories:
🤝 Support & Contributing
- Bug Reports: GitHub Issues
- Code Contributions: Pull Requests are welcome!
📄 License
This project is licensed under the Mozilla Public License 2.0.
Start making AI your code repository management partner! 🚀
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
An MCP server for managing your repositories on Forgejo/Gitea server.
Related MCP Servers
- AsecurityAlicenseAqualityMCP Tool Server for Gitee, supporting the management of repository files/branches, Issues, and Pull Requests.Last updated -206747TypeScriptMIT License
- AsecurityFlicenseAqualityMCP server for managing Git operations on local repositories, allowing users to list repositories, get and create tags, list commits, push tags, and refresh repositories through a standardized interface.Last updated -63Python
- -securityAlicense-qualityAn MCP server that enables communication with GitLab repositories, allowing interaction with GitLab's API to manage projects, issues, and repositories through natural language.Last updated -3,8051JavaScriptMIT License
- -securityFlicense-qualityAn MCP server that enables Git repository operations and GitHub PR workflows, allowing users to manage repositories, create branches, commit changes, and create pull requests through natural language.Last updated -1Python