Docmost MCP Server
Enables AI agents to search, create, modify, and organize documentation pages and spaces in Docmost.
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 byupdatedAtdescending).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_pagetool 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.