Gitee MCP Server Integration

What does “Gitee” MCP Server do?

Gitee MCP Server is a Model Context Protocol (MCP) server implementation specifically designed to interface with Gitee, a popular Git repository hosting platform. By leveraging the MCP standard, the Gitee MCP Server empowers AI assistants to seamlessly interact with Gitee’s APIs. This allows developers and AI agents to perform tasks such as managing repositories, handling issues, working with pull requests, and monitoring notifications. It is well-suited for enhancing development workflows by automating routine repository operations, integrating with other tools, and enabling complex actions like dynamic toolset enable/disable and supporting both personal and organizational use cases. Its flexible configuration and compatibility with different Gitee instances further extend its utility for enterprise environments.

List of Prompts

No prompt templates are mentioned in the repository or documentation.

List of Resources

No explicit list of MCP resources exposed by the server is provided in the repository or documentation.

List of Tools

• Interact with Gitee repositories: Enables AI assistants to access and manage Gitee repositories.
• Issue management: Provides the ability to obtain, comment on, and close issues within repositories.
• Pull request management: Allows creation and handling of pull requests based on issue details.
• Notifications handling: Lets AI assistants interact with notifications from Gitee.

Note: The above tools are inferred from the README.md, as there is no server.py and the exact function names are not listed.

Use Cases of this MCP Server

• Repository Management: Automate repository tasks such as creation, configuration, and access management, reducing manual steps for developers.
• Issue Tracking and Resolution: Retrieve issues, comment, and close them efficiently, streamlining bug tracking and project management.
• Automated Pull Requests: Facilitate the implementation of changes and automated pull request creation in response to issue resolutions.
• Enterprise & Organization Operations: Support for both personal and organization/enterprise use, making it suitable for teams and companies managing multiple projects.
• Notification Aggregation: Collect and process notifications from Gitee, improving awareness and response time to important repository events.

How to set it up

Windsurf

1. Ensure you have Go 1.23.0+ and a Gitee account with an access token.

2. Open your Windsurf configuration file.

3. Add the Gitee MCP Server to the mcpServers section:

   {
     "mcpServers": {
       "gitee": {
         "command": "npx",
         "args": ["-y", "@gitee/mcp-gitee@latest"]
       }
     }
   }
   

4. Save the file and restart Windsurf.

5. Verify the server connection from the Windsurf interface.

Securing API Keys:

{
  "mcpServers": {
    "gitee": {
      "command": "npx",
      "args": ["-y", "@gitee/mcp-gitee@latest"],
      "env": {
        "GITEE_ACCESS_TOKEN": "<your_personal_access_token>"
      }
    }
  }
}

Claude

1. Install Go 1.23.0+ and obtain a Gitee access token.

2. Open Claude’s configuration file.

3. Insert the server definition:

   {
     "mcpServers": {
       "gitee": {
         "command": "npx",
         "args": ["-y", "@gitee/mcp-gitee@latest"]
       }
     }
   }
   

4. Save and restart Claude.

5. Confirm the MCP server is active.

Securing API Keys:

{
  "mcpServers": {
    "gitee": {
      "command": "npx",
      "args": ["-y", "@gitee/mcp-gitee@latest"],
      "env": {
        "GITEE_ACCESS_TOKEN": "<your_personal_access_token>"
      }
    }
  }
}

Cursor

1. Make sure Go 1.23.0+ is installed and you have a Gitee access token.

2. Edit your Cursor configuration file.

3. Add the MCP server entry:

   {
     "mcpServers": {
       "gitee": {
         "command": "npx",
         "args": ["-y", "@gitee/mcp-gitee@latest"]
       }
     }
   }
   

4. Save changes and restart Cursor.

5. Verify the setup through the Cursor UI.

Securing API Keys:

{
  "mcpServers": {
    "gitee": {
      "command": "npx",
      "args": ["-y", "@gitee/mcp-gitee@latest"],
      "env": {
        "GITEE_ACCESS_TOKEN": "<your_personal_access_token>"
      }
    }
  }
}

Cline

1. Ensure Go 1.23.0+ is available and you possess a Gitee access token.

2. Access and modify Cline’s config file.

3. Add the following MCP server configuration:

   {
     "mcpServers": {
       "gitee": {
         "command": "npx",
         "args": ["-y", "@gitee/mcp-gitee@latest"]
       }
     }
   }
   

4. Save your changes and restart Cline.

5. Check that the server initializes properly.

Securing API Keys:

{
  "mcpServers": {
    "gitee": {
      "command": "npx",
      "args": ["-y", "@gitee/mcp-gitee@latest"],
      "env": {
        "GITEE_ACCESS_TOKEN": "<your_personal_access_token>"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "gitee": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “gitee” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available information, the Gitee MCP Server provides clear value for Gitee API integration but lacks documented prompt templates and explicit resource listing, and there is no mention of roots or sampling features. Its setup is well-documented and it supports key repository automation features.

MCP Score

How would I rate this MCP?
Considering the documentation, available features, and openness (MIT license), but also the lack of explicit resource/prompt/sampling/root documentation, I would rate this MCP Server at 6/10. It is functional and open, but could be improved with more thorough MCP-specific documentation and support for advanced MCP features.