YuQue MCP
An MCP server for interacting with the YuQue knowledge base, enabling AI assistants to perform operations on documents and information.
语雀 MCP 服务器
基于 go-zero MCP 组件开发的语雀 Model Context Protocol 服务器,为 AI 助手提供语雀知识库操作能力。
功能特性
- 🔍 获取文档: 根据知识库ID和文档ID获取文档详细内容
- 📝 创建文档: 在指定知识库中创建新文档
- ✏️ 更新文档: 修改文档标题、内容等信息
- 🔎 搜索文档: 在语雀中搜索相关文档
- 👤 用户信息: 获取当前用户详细信息
快速开始
1. 设置环境变量
export YUQUE_TOKEN="your_yuque_token_here"
2. 安装依赖
go mod tidy
3. 启动服务器
go run cmd/server/main.go -f config.yaml
服务器将在 http://localhost:8080 启动。
可用工具
yuque_get_current_user
获取当前语雀用户信息。
yuque_get_document
获取指定文档内容。
book_id: 知识库ID或路径doc_id: 文档ID或slug
yuque_create_document
创建新文档。
book_id: 知识库ID或路径title: 文档标题body: 文档内容(可选)format: 文档格式,默认markdownpublic: 公开设置,默认0(私密)
yuque_update_document
更新文档内容。
book_id: 知识库ID或路径doc_id: 文档ID或slugtitle: 新标题(可选)body: 新内容(可选)format: 文档格式(可选)public: 公开设置(可选)
yuque_search_documents
搜索文档。
query: 搜索关键词
配置说明
配置文件 config.yaml:
name: yuque-mcp-server
host: localhost
port: 8080
mcp:
name: yuque-mcp-server
messageTimeout: 30s
cors:
- http://localhost:3000
yuque:
baseUrl: "https://www.yuque.com/api/v2"
# token 通过环境变量 YUQUE_TOKEN 设置
Cursor IDE 集成配置
在 Cursor IDE 中使用此 MCP 服务器,需要在设置中添加以下配置:
{
"mcpServers": {
"yuque": {
"command": "go",
"args": ["run", "cmd/server/main.go", "-f", "config.yaml"],
"cwd": "/path/to/YuQueMCP",
"env": {
"YUQUE_TOKEN": "your_yuque_token_here"
}
}
}
}
配置步骤:
- 打开 Cursor IDE 设置
- 搜索 "MCP" 或 "Model Context Protocol"
- 添加上述 JSON 配置
- 将
cwd路径修改为项目实际路径 - 将
YUQUE_TOKEN替换为你的语雀 API Token - 重启 Cursor IDE
项目结构
├── cmd/server/ # 服务器启动入口
├── internal/
│ ├── config/ # 配置相关
│ ├── server/ # MCP服务器逻辑
│ │ └── tools/ # 工具实现
│ └── yuque/ # 语雀API客户端
├── config.yaml # 配置文件
└── go.mod # Go模块文件
Serveurs connexes
Readwise Reader
An MCP server for the Readwise Reader API to access and manage your articles and highlights.
Intelligence Aeternum Data Portal
The complete creative AI pipeline exposed as MCP tools. From generation to permanent storage — every stage available via x402 USDC micropayments on Base L2.
context-distill
context-distill is an MCP server that compresses noisy command output into precise, actionable summaries for LLM workflows. Use distill_batch for large logs and distill_watch for cycle-to-cycle deltas. Built with Go, Cobra, Viper, and DI for reliable local and provider-backed distillation.
Backcast MCP Server
The Outcome Backcasting MCP is a strategic planning tool that helps you work backwards from a desired future outcome to identify the specific steps, resources, and dependencies needed to achieve your goals. Unlike traditional forward planning, backcasting starts with your end goal and creates a reverse roadmap to get there.
Atlassian Confluence
Interact with Atlassian Confluence Cloud spaces, pages, and content in real-time.
Unreasonable Thinking Server
A tool for bold and unconventional problem-solving, generating unique solutions by branching and tracking thoughts.
EAN-Search.org product database official MCP
Access to the EAN-Search.org product database, searching by barcode or keywords
Jira Weekly Reporter
Connects to a Jira instance to generate weekly reports based on issue activity.
Canvas LMS
MCP server for easy access to education data through your Canvas LMS instance.
Doc Lib MCP
An MCP server for document ingestion, chunking, semantic search, and note management.