-
securityA
license-
qualitylark-tools-mcp connects Lark and cursor.
It provides cursor with the ability to read documents, send messages, process tasks, and perform data analysis.
Last updated -
26
JavaScript
MIT License
The open-docs-mcp server is an open-source MCP implementation for document management that allows you to:
- Crawl and index documentation from various sources in multiple formats
- Enable/disable crawling for specific documentation sources
- Force re-crawl enabled documents
- Search documentation with filters and pagination
- Build or rebuild search index
- List all available documents including disabled ones
- List enabled documents with their cache status
- Integrate with MCP protocol for AI context and resource-based document access
These features essentially replicate Cursor's @Docs functionality through the MCP API.
Supports indexing and searching of Markdown-formatted documentation, enabling access to content in this format through the document management system.
Runs as a Node.js application, with specific version requirements (>=16.0.0) to enable the document management functionality.
Built with TypeScript 4.9.5, providing type safety and modern language features for the document management implementation.
open-docs-mcp MCP Server
An open-source MCP implementation providing document management functionality. 中文文档
Features
Document Management
- Crawl and index documentation from various sources
- Support for multiple document formats
- Full-text search capabilities
MCP Server API
- Resource-based access to documents
- Tool-based document management
Available Tools
- enable_doc - Enable crawling for a specific doc
- disable_doc - Disable crawling for a specific doc
- crawl_docs - Start crawling enabled docs
- build_index - Build search index for docs
- search_docs - Search documentation
- list_enabled_docs - List enabled docs
- list_all_docs - List all available docs
Cursor @Docs Compatibility
This project aims to replicate Cursor's @Docs functionality by providing:
- Document Indexing:
- Crawl and index documentation from various sources
- Support for multiple document formats (HTML, Markdown, etc.)
- Automatic re-indexing to keep docs up-to-date
- Document Access:
- Search across all indexed documentation
- Integration with MCP protocol for AI context
- Custom Docs Management:
- Add new documentation sources via
enable_doctool - Manage enabled docs via
list_enabled_docstool - Force re-crawl with
crawl_docstool
- Add new documentation sources via
Architecture
Usage
Installing via Smithery
To install Document Management Server for Claude Desktop automatically via Smithery:
Configuration
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Configuration Options:
command: Node.js executableargs: Array of arguments to pass to the script--docsDir: Required, specifies docs directory path
disabled: Set to true to temporarily disable the serveralwaysAllow: Array of tool names that can be used without confirmation
Development
Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
License
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
An open-source MCP implementation providing document management functionality. This project aims to replicate Cursor's @Docs functionality.
Related MCP Servers
- -securityAlicense-qualityAn open-source MCP server that provides applications like Cursor, Windsurf, and Claude with access to llms.txt documentation files, allowing users to control and audit context retrieval.Last updated -4PythonMIT License
- -securityFlicense-qualityA tool that generates MCP servers for Smithery with Cursor IDE integration, allowing users to quickly create servers from templates such as Basic, Web Search, or Database interactions.Last updated -JavaScript
- -securityFlicense-qualityAn MCP server that enables generating scripts based on specified topics and keywords, while also providing functionality to store and summarize notes.Last updated -Python