Documize MCP Server

Documize MCP Server

A Model Context Protocol (MCP) server that provides seamless integration with the Documize API. This server enables AI assistants like Claude to interact with your Documize knowledge base - search documents, manage spaces, handle attachments, and more.

Category
访问服务器

README

Documize MCP Server

A Model Context Protocol (MCP) server that provides seamless integration with the Documize API. This server enables AI assistants like Claude to interact with your Documize knowledge base - search documents, manage spaces, handle attachments, and more.

npm version License: MIT

Features

  • 🔍 Search: Full-text search across documents and content
  • 📄 Documents: Complete CRUD operations for documents
  • 📝 Pages: Granular page-level content management
  • 📁 Spaces: Manage spaces and permissions
  • 📎 Import/Export: Import documents (HTML/Markdown/Word) and export (PDF/HTML/DOCX)
  • 👥 Users & Groups: User and group management
  • 🧪 Well-Tested: 92.68% code coverage with comprehensive unit tests
  • Reliable: Automatic retry logic for transient errors

Complete Tool List (24 Tools)

Documents (4 tools)

  • get_document - Get document by ID with content and metadata
  • list_documents - List all documents in a space
  • update_document - Update existing document
  • delete_document - Delete a document

Note: Documents can only be created via import_document (see Import/Export tools)

Pages (5 tools)

  • get_pages - Get all pages in a document
  • get_page - Get a specific page
  • create_page - Create new page with HTML content
  • update_page - Update existing page
  • delete_page - Delete a page

Spaces (4 tools)

  • list_spaces - List all available spaces
  • get_space - Get space details
  • create_space - Create new space
  • delete_space - Delete a space

Users (3 tools)

  • list_users - List all users
  • create_user - Create new user
  • delete_user - Delete a user

Groups (2 tools)

  • list_groups - List all groups
  • join_group - Add user to group
  • leave_group - Remove user from group

Import/Export (4 tools)

  • import_document - Import HTML, Markdown, or Word files (creates new documents)
  • export_pdf - Export document as PDF
  • export_html - Export document as HTML
  • export_docx - Export document as DOCX

Note: Document creation is only possible via import_document

Search (1 tool)

  • search - Full-text search across documents, spaces, and attachments

Quick Start

Installation

npm install -g documize-mcp-server

Configuration

  1. Get your Documize credentials:

    • Domain (usually empty for self-hosted instances)
    • Email
    • Password
  2. Encode credentials:

    # For self-hosted (domain is empty)
    echo -n ":email:password" | base64
    
    # For multi-tenant (with domain)
    echo -n "domain:email:password" | base64
    
  3. Configure for Claude Desktop:

    Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

    {
      "mcpServers": {
        "documize": {
          "command": "documize-mcp-server",
          "env": {
            "DOCUMIZE_API_URL": "https://your-instance.com",
            "DOCUMIZE_API_CREDENTIALS": "your-base64-credentials"
          }
        }
      }
    }
    
  4. Restart Claude Desktop

VS Code GitHub Copilot

  1. Install the server:

    npm install -g documize-mcp-server
    
  2. Configure .vscode/mcp.json in your workspace:

    {
      "mcpServers": {
        "documize": {
          "command": "documize-mcp-server",
          "env": {
            "DOCUMIZE_API_URL": "https://your-instance.com",
            "DOCUMIZE_API_CREDENTIALS": "your-base64-credentials"
          }
        }
      }
    }
    
  3. Reload VS Code

Usage Examples

See QUICKSTART.md for detailed examples and docs/API-REFERENCE.md for complete API documentation.

Search Documents

Search for documents about "project requirements"

Import Document (Create)

Import this HTML file into the Engineering space to create a new document:
<h1>Meeting Notes</h1><p>Discussion about project requirements...</p>

Manage Pages

Add a new section to document abc123 with title "Introduction"

Import Document

Import the markdown file README.md into the Documentation space

Export Document

Export document abc123 as PDF

Development

Prerequisites

  • Node.js 18+
  • npm or yarn
  • A Documize instance with API access

Setup

git clone https://github.com/artfulhacker/documize-mcp-server.git
cd documize-mcp-server
npm install

Build

npm run build

Testing

Run the full test suite with coverage:

npm test              # Run all tests once
npm run test:watch    # Run tests in watch mode
npm run test:ui       # Run tests with interactive UI
npm run test:coverage # Run with coverage report

Test Coverage: 92.68% (68 tests across 7 test suites)

Integration Testing

Run integration tests against a live Documize instance:

npm run integration-test

Note: Integration tests require valid credentials in .env file.

Test with MCP Inspector

npm run inspector

API Documentation

Project Status

Version: 1.1.0
Status: Production Ready
Test Coverage: 92.68% (68 unit tests + integration tests)
Tools: 24 MCP tools covering complete Documize API
Features: Auto-retry logic, comprehensive error handling, full TypeScript support

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

Security

See SECURITY.md for security considerations and best practices.

License

MIT License - see LICENSE for details.

Links

  • Repository: https://github.com/artfulhacker/documize-mcp-server
  • Issues: https://github.com/artfulhacker/documize-mcp-server/issues
  • NPM: https://www.npmjs.com/package/documize-mcp-server
  • Changelog: CHANGELOG.md

Acknowledgments

Built with the Model Context Protocol by Anthropic.


Made by @artfulhacker

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选