by normal-coder
Integrate with Gitee to manage repositories, track issues, and streamline code workflows easily using secure token authe
Connects AI assistants to Gitee repositories for managing code, issues, and pull requests. Enables automated Git workflows through simple token authentication.
Gitee is a community-built MCP server published by normal-coder that provides AI assistants with tools and capabilities via the Model Context Protocol. Integrate with Gitee to manage repositories, track issues, and streamline code workflows easily using secure token authe It is categorized under developer tools, productivity.
You can install Gitee in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Gitee is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Useful MCP listing: Gitee is the kind of server we cite when onboarding engineers to host + tool permissions.
We evaluated Gitee against two servers with overlapping tools; this profile had the clearer scope statement.
Gitee has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
Useful MCP listing: Gitee is the kind of server we cite when onboarding engineers to host + tool permissions.
According to our notes, Gitee benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Gitee reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
We evaluated Gitee against two servers with overlapping tools; this profile had the clearer scope statement.
Strong directory entry: Gitee surfaces stars and publisher context so we could sanity-check maintenance before adopting.
Gitee is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
We wired Gitee into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
showing 1-10 of 28
Let AI operate Gitee repositories/Issues/Pull Requests for you through MCP
<img width="380" height="200" src="https://glama.ai/mcp/servers/cck9xigm1d/badge" />
| Category | MCP Tool | Description |
|---|---|---|
| Repository Operations | create_repository | Create a Gitee repository |
fork_repository | Fork a Gitee repository | |
| Branch Operations | create_branch | Create a new branch in a Gitee repository |
list_branches | List branches in a Gitee repository | |
get_branch | Get details of a specific branch in a Gitee repository | |
| File Operations | get_file_contents | Get contents of a file or directory in a Gitee repository |
create_or_update_file | Create or update a file in a Gitee repository | |
push_files | Push multiple files to a Gitee repository | |
| Issue Operations | create_issue | Create an Issue in a Gitee repository |
list_issues | List Issues in a Gitee repository | |
get_issue | Get details of a specific Issue in a Gitee repository | |
update_issue | Update an Issue in a Gitee repository | |
add_issue_comment | Add a comment to an Issue in a Gitee repository | |
| Pull Request Operations | create_pull_request | Create a Pull Request in a Gitee repository |
list_pull_requests | List Pull Requests in a Gitee repository | |
get_pull_request | Get details of a specific Pull Request in a Gitee repository | |
update_pull_request | Update a Pull Request in a Gitee repository | |
merge_pull_request | Merge a Pull Request in a Gitee repository | |
| User Operations | get_user | Get Gitee user information |
get_current_user | Get authenticated Gitee user information |
To install Gitee MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @normal-coder/gitee-mcp-server --client claude
GITEE_API_BASE_URL: Optional, Gitee OpenAPI Endpoint, default is https://gitee.com/api/v5GITEE_PERSONAL_ACCESS_TOKEN: Required, Gitee account personal access token (PAT), can be obtained from Gitee account settings Personal Access TokensDEBUG: Optional, set to true to enable debug logging, default is disabled{
"mcpServers": {
"Gitee": {
"command": "npx",
"args": [
"-y",
"gitee-mcp-server"
],
"env": {
"GITEE_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
}
}
}
}
# Get from DockerHub
docker pull normalcoder/gitee-mcp-server
# Build locally
docker build -t normalcoder/gitee-mcp-server .
{
"mcpServers": {
"Gitee": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GITEE_PERSONAL_ACCESS_TOKEN",
"normalcoder/gitee-mcp-server"
],
"env": {
"GITEE_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
}
}
}
}
npm install
npm run build
After successful build, /dist will contain the runnable MCP server.
npm start
The MCP server will run on stdio, allowing it to be used as a subprocess by MCP clients.
You can also run the server using Docker:
docker build -t normalcoder/gitee-mcp-server .
Run MCP Server with Docker:
docker run -e GITEE_PERSONAL_ACCESS_TOKEN=<YOUR_TOKEN> normalcoder/gitee-mcp-server
You can use @modelcontextprotocol/inspector for debugging:
Create a .env file in the root directory for environment variables:
GITEE_API_BASE_URL=https://gitee.com/api/v5
GITEE_PERSONAL_ACCESS_TOKEN=<YOUR_TOKEN>
Run the debug tool to start the service and web debug interface:
npx @modelcontextprotocol/inspector npm run start --env-file=.env
The project includes a debug() function for printing debug information, usage:
import { debug } from './common/utils.js';
debug('Message to log');
debug('Message with data:', { key: 'value' });
Debug logs are only printed when the DEBUG environment variable is set to true.
@modelcontextprotocol/sdk: MCP SDK for server implementationuniversal-user-agent: For generating user agent stringszod: For schema validationzod-to-json-schema: For converting Zod schemas to JSON schemasLicensed under MIT License. You are free to use, modify and distribute the software, subject to the terms and conditions of the MIT License. For more details, see the LICENSE file in the project repository.
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.