Gitee MCP Server

io.github.PaulSethPublished by GitHub account PaulSethv0.1.0Updated Oct 24, 2026

让 AI 用自然语言管理 Gitee 仓库：查 star、管 Issue、基于 commit 生成中文 CHANGELOG（原生无此 API）

VerifiedSTDIODesktop onlyProductivity & WorkflowDeveloper Tools

Overview

AI-generated overview

A local MCP server that lets an AI assistant manage Gitee repositories in natural language: repository stats, issues, stargazers and Chinese CHANGELOGs from git

What you can do
Read repository statistics such as stars, forks, watches and open issue counts, and list the users who starred a repository (requires a token). List issues filtered by status or label, create new issues, and update issue status or labels, including auto-tagging and closing. Generate a Chinese CHANGELOG from recent commits, since Gitee has no native CHANGELOG API. Expose a repository resource returning stats plus a snapshot of the last five commits for the assistant to read directly.
When to use it
Useful when you work with Gitee-hosted projects and want an assistant to check repository popularity, triage or file issues, or draft a Chinese CHANGELOG from commit history without leaving the chat. It can be tried without a token in mock mode for demonstration.
Requirements
Runs locally over stdio, typically via npx or a local Node.js build. A Gitee personal access token in GITEE_ACCESS_TOKEN is needed for real mode and is mandatory for stargazer and subscriber endpoints; without it the server runs in mock mode with local snapshot data. An optional GITEE_MODE variable forces mock or real mode. Network access to the Gitee API is required in real mode.
Before you install
The token grants access to your Gitee account and should be scoped to the projects permission only; keep it out of shared configuration. In real mode the assistant can create issues and change issue status and labels, which modifies repository data. Without a token, results come from local mock snapshots and do not reflect the live repository.

Installation

In SourceWeft

  1. Open Gitee MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Gitee MCP Server

让任意 AI 模型用自然语言管理 Gitee 仓库的 MCP Server。

[License: MIT] [npm version] [Glama]

一句话就能替你管 Gitee："social-media-bot-cn-generic 现在多少 star？" "给这几个 issue 打上 bug 标签" "基于最近 commit 帮我生成一份中文 CHANGELOG 贴进 README"。

本 Server 是 MCP（Model Context Protocol） 标准实现，可接入任何支持 MCP 的 AI 客户端（WorkBuddy / Claude Desktop / Cursor / 任意 Agent 框架）。

✨ 功能（v1）

工具作用
get_repo_stats仓库统计：star / fork / watch / 开放 issue 数
list_stargazers列出点 star 的用户（⚠️ 需 PAT）
list_issues列出 Issue，支持按状态/标签过滤
create_issue新建 Issue（收需求/建任务）
update_issue更新 Issue 状态/标签（自动打标签/关单）
generate_changelog基于 commit 生成中文 CHANGELOG（Gitee 无原生 API，靠 commits 组合拼出）

资源：gitee://repo/{owner}/{repo} —— 返回仓库统计 + 最近 5 条 commit 快照，AI 可直接读取。

🚀 快速开始

方式一：npx 直接运行（推荐，无需克隆）

bash
npx -y gitee-mcp

首次运行会自动下载；默认 Mock 模式，无需 token 即可演示。

方式二：源码运行

bash
git clone https://gitee.com/jokerbhind/gitee-mcp-server.gitcd gitee-mcp-servernpm installnpm run buildnpm start          # 默认 Mock 模式，无需 token 即可演示

接 WorkBuddy / Claude Desktop

在 ~/.workbuddy/mcp.json（或对应 MCP 配置）中加入：

json
{  "mcpServers": {    "gitee-mcp-server": {      "command": "npx",      "args": ["-y", "gitee-mcp"]    }  }}

或使用本地构建产物（command 用绝对路径的 node，避免客户端不继承 PATH）：

json
{  "mcpServers": {    "gitee-mcp-server": {      "command": "C:/绝对路径/node.exe",      "args": ["H:/绝对路径/gitee-mcp-server/build/index.js"]    }  }}

🔑 真实模式（Real）

复制 .env.example 为 .env 并填入 Gitee 私人令牌：

bash
cp .env.example .env# 编辑 .env：填入 GITEE_ACCESS_TOKEN
变量说明
GITEE_ACCESS_TOKENGitee 私人令牌（设置 → 私人令牌，勾选 projects 权限）。stargazers/subscribers 接口强制鉴权，无 token 会 401
GITEE_MODE留空=自动判定；mock=强制演示；real=强制真实（缺 token 自动回退 mock 并告警）

Server 会自动从项目根目录的 .env 读取（无需设置 cwd），填好 token 后即自动切 Real 模式。

🐶 Dogfood 示例

本项目本身就用 generate_changelog 给 jokerbhind/social-media-bot-cn-generic 生成 CHANGELOG。真实 commit 输出示例：

markdown
## CHANGELOG · jokerbhind/social-media-bot-cn-generic
> 基于最近 1 条 commit 自动生成（Gitee MCP Server）
### ✨ 新功能- feat: 社媒客服 Bot 泛用版 Starter Kit _by PaulSeth（2026-09-03）_

这就是「gap filler」的溢价逻辑：Gitee 官方没有 CHANGELOG API，本 Server 用现成的 /commits 组合出人人想要的能力。

🧩 架构

AI 模型 ←→ MCP(STDIO) ←→ GiteeMcpServer                                │                         GiteeService（Mock/Real 双模式路由）                           ├─ mock.ts  本地快照（无凭证可演示）                           └─ api.ts   Gitee API v5（填 token 后生效）

Mock 模式让公开仓库也能 npm start 直接演示、被 Glama 自动收录，且不泄露任何凭证。

📦 发布与收录

目标状态做法
Gitee 公开仓✅ 已上线https://gitee.com/jokerbhind/gitee-mcp-server
GitHub 镜像仓✅ 已上线https://github.com/PaulSeth/gitee-mcp-server
npm✅ 已发布 v0.1.0https://www.npmjs.com/package/gitee-mcp
Glama✅ 已提交并通过构建检查提交 GitHub 镜像仓 URL 后由 Glama 自动生成镜像跑安全/质量检查
MCP Registry⏳ 待发布mcp-publisher login github + mcp-publisher publish（读仓库根 server.json）

本项目的 CHANGELOG.md 由 本 Server 的 generate_changelog 工具自己生成（dogfood）。

Glama 索引的是 GitHub 仓库，故需先将本仓库镜像到 GitHub 再提交。

🗺️ Roadmap（Phase 2，按需再做）

  • comment_on_issue/pr：AI 自动回复
  • webhook_auto_label：监听 Webhook 自动打标签
  • gitee_to_github_mirror：Gitee↔GitHub 双平台镜像
  • list_pulls / merge_pull：PR 管理
  • create_release：基于 CHANGELOG 自动发版

📄 License

MIT © 2026 Paul (Gitee: jokerbhind / GitHub: PaulSeth)

Source: README.md at commit ff3afb1

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts