Open Docs Mcp: Multi-Cloud Collaboration & Real-Time Edits

Open Docs Mcp: Effortless multi-cloud document collaboration. Real-time edits, secure sharing, seamless teamwork. Boost productivity, today!

Visit Repository

✨ Developer Tools

4.5(112 reviews)

168 saves

78 comments

Users create an average of 48 projects per month with this tool

About Open Docs Mcp

What is Open Docs Mcp: Multi-Cloud Collaboration & Real-Time Edits?

This open-source project replicates Cursor's @Docs functionality, enabling teams to manage documentation across multiple cloud environments. It acts as an MCP (Multi-Cloud Protocol) server that crawls, indexes, and serves docs in real-time. Think of it as a Swiss Army knife for developers needing to sync technical documentation between tools like Claude Desktop and their own systems.

How to Use Open Docs Mcp: Multi-Cloud Collaboration & Real-Time Edits?

Quick setup requires two steps:

Configure your docs directory via command line:

npx -y open-docs-mcp --docsDir /your/document/path

Integrate with apps like Claude Desktop by adding this config block to your app's settings file:

{
  "mcpServers": {
    "open-docs-mcp": {
      "command": "npx",
      "args": ["-y", "open-docs-mcp", "--docsDir", "/path/to/your/docs"]
    }
  }
}

Pro tip: Use npm run watch during development to auto-reload changes

Open Docs Mcp Features

Key Features of Open Docs Mcp: Multi-Cloud Collaboration & Real-Time Edits?

Universal Document Handling: Supports HTML, Markdown, PDFs, and more through format conversion pipelines
Smart Maintenance: Automatic re-indexing when source docs change (like GitHub repo updates)
Toolbelt Power: 7 built-in tools for managing docs (enable/disable/crawl/search)
Security First: Granular access control via MCP protocol integration

Under the hood, the architecture uses three core modules: Crawler (fetches docs), Search Engine (indexes content), and MCP Server (exposes API endpoints)

Use Cases of Open Docs Mcp: Multi-Cloud Collaboration & Real-Time Edits?

Popular scenarios include:

Syncing internal developer docs between cloud environments
Automating Jira/Knowledge Base updates via webhooks
Creating self-updating AI training corpora
Powering real-time help systems in SaaS platforms

Example: A dev team uses crawl_docs

Open Docs Mcp FAQ

FAQ from Open Docs Mcp: Multi-Cloud Collaboration & Real-Time Edits?

Does it work with non-technical documentation?: Yes! The crawler handles any text-based format. Try using Pandoc for exotic formats
How do I debug issues?: Run npm run inspector to attach a Node.js debugger. Check logs for "indexing failures"
Can I use this with self-hosted tools?: Absolutely. The MIT license allows embedding in commercial products. Just remember to include the license text
What's the performance like?: Tested with 10k+ docs in a single index. Use Elasticsearch for enterprise-scale deployments

Content

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_doc` tool
* Manage enabled docs via `list_enabled_docs` tool
* Force re-crawl with `crawl_docs` tool

Architecture

┌───────────────────────────────────────────────────────┐
│                    open-docs-mcp Server                    │
├───────────────────┬───────────────────┬───────────────┤
│   Crawler Module  │  Search Engine    │  MCP Server   │
├───────────────────┼───────────────────┼───────────────┤
│ - Web crawling    │ - Full-text index │ - Resources   │
│ - Doc conversion  │ - Relevance score │ - Tools       │
│ - Storage         │ - Query parsing   │ - Prompts     │
└───────────────────┴───────────────────┴───────────────┘

Usage

npx -y open-docs-mcp --docsDir ./docs

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

{
  "mcpServers": {
    "open-docs-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "open-docs-mcp",
        "--docsDir",
        "/path/to/docs"
      ]
    }
  }
}

Configuration Options:

command: Node.js executable
args: Array of arguments to pass to the script
- --docsDir: Required, specifies docs directory path
disabled: Set to true to temporarily disable the server
alwaysAllow: Array of tool names that can be used without confirmation

Development

npm run watch  # Auto-rebuild on changes
npm run inspector  # Debug with MCP Inspector

Documentation

Full documentation is available in the docs directory.

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

MIT