Docmost MCP Server

Docmost MCP Server

Enables AI agents to search, create, modify, and organize documentation pages and spaces in Docmost.

Category
访问服务器

README

Docmost MCP Server

A Model Context Protocol (MCP) server for Docmost, enabling AI agents to search, create, modify, and organize documentation pages and spaces.

Features

Core Management

  • create_page: Smart creation tool. Creates content (via import) AND handles hierarchy (nesting under a parent) in one go.
  • update_page: Update a page's content and/or title. Updates are performed via real-time collaboration (WebSocket).
  • delete_page / delete_pages: Delete single or multiple pages at once.
  • move_page: Organize pages hierarchically by moving them to a new parent or root.

Exploration & Retrieval

  • search: Full-text search across spaces with optional space filtering (query, spaceId).
  • get_workspace: Get information about the current Docmost workspace.
  • list_spaces: View all spaces within the current workspace.
  • list_groups: View all groups within the current workspace.
  • list_pages: List pages within a space (ordered by updatedAt descending).
  • get_page: Retrieve full content and metadata of a specific page.

Technical Details

  • Automatic Markdown Conversion: Page content is automatically converted from Docmost's internal ProseMirror/TipTap JSON format to clean Markdown for easy agent consumption. Supports all Docmost extensions including callouts, task lists, math blocks, embeds, and more.
  • Smart Import API: Uses Docmost's import API to ensure clean Markdown-to-ProseMirror conversion when creating pages.
  • Child Preservation: The update_page tool creates a new page ID but effectively simulates an in-place update by reparenting existing child pages to the new version.
  • Pagination Support: Automatically handles pagination for large datasets (spaces, pages, groups).
  • Filtered Responses: API responses are filtered to include only relevant information, optimizing data transfer for agents.

Installation

npm install
npm run build

Configuration

This server requires the following environment variables to be set:

  • DOCMOST_API_URL: The full URL to your Docmost API (e.g., https://docs.example.com/api).
  • DOCMOST_EMAIL: The email address for authentication.
  • DOCMOST_PASSWORD: The password for authentication.

usage with Claude Desktop / generic MCP Client

Add the following to your MCP configuration (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "docmost-local": {
      "command": "node",
      "args": ["./build/index.js"],
      "env": {
        "DOCMOST_API_URL": "http://localhost:3000/api",
        "DOCMOST_EMAIL": "test@docmost.com",
        "DOCMOST_PASSWORD": "test"
      }
    }
  }
}

Development

# Watch mode
npm run watch

# Build
npm run build

License

MIT

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