What are the prerequisites for running the server locally?
Go 1.23.0 or higher and a Gitee account with a personal access token are required.
@oschina
mcp-gitee is a Model Context Protocol (MCP) server implementation for Gitee. It provides a set of tools that interact with Gitee's API, allowing AI assistants to manage repository, issues, pull requests, etc.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"gitee": {
"command": "mcp-gitee",
"env": {
"GITEE_API_BASE": "https://gitee.com/api/v5",
"GITEE_ACCESS_TOKEN": "<your personal access token>"
}
}
}
}Repository
Repository
Repository
Repository
Repository
Repository
Repository
Repository
Repository
Pull Request
Pull Request
Pull Request
Pull Request
Pull Request
Pull Request
Pull Request
Comment
Comment
Issue
Issue
Issue
Issue
User
User
Notification
Gitee MCP Server is a Model Context Protocol (MCP) server implementation for Gitee. It provides a set of tools for interacting with Gitee's API, allowing AI assistants to manage repositories, issues, pull requests, and more. It is intended for developers and teams using Gitee who want to automate workflows via MCP-compatible hosts like Claude, Cursor, or Codex.
You can use the server either as a remote MCP service (no installation required) or run it locally after building from source. For the remote server, configure your MCP host with the URL https://api.gitee.com/mcp and a Bearer token from your Gitee personal access tokens. For local use, clone the repository, build with make build, and run mcp-gitee with flags such as --token, --api-base, --transport, and --address. Tools can be enabled or disabled via command-line flags or per-request HTTP headers.
Go 1.23.0 or higher and a Gitee account with a personal access token are required.
Yes, the official remote MCP server is available at `https://api.gitee.com/mcp`. No local installation is needed; just configure your MCP host with the correct URL and authorization header.
The server supports stdio, sse, and http transports, configurable via the `--transport` flag.
You can use the `--enabled-toolsets` (whitelist) or `--disabled-toolsets` (blacklist) command-line flags, or the corresponding environment variables. When using the remote HTTP/SSE server, you can also pass `X-MCP-Enabled-Tools` or `X-MCP-Disabled-Tools` headers per request. Whitelist takes precedence over blacklist.
Yes, when using the remote MCP server (HTTP/SSE transport), you can dynamically filter tools by adding the `X-MCP-Enabled-Tools` or `X-MCP-Disabled-Tools` HTTP headers with a comma-separated list of tool names.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
コメント