Open Docs MCP Server

@askme765cs

代码仓库

基本信息

分类

记忆与知识

传输方式

stdio

作者

askme765cs

提交者

askme765cs

关于 Open Docs MCP Server

暂无概览

#open-docs-mcp#document-management #mcp-server

Open Docs MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

Open Docs MCP Server 工具

Enable crawling for a specific doc

Disable crawling for a specific doc

Start crawling enabled docs

Build search index for docs

Search documentation

Build search index for docs

List all enabled docs with their cache status

List all available docs including disabled ones

概览

What is Open Docs Mcp?

Open Docs Mcp is an open-source MCP server that provides document management functionality. It crawls and indexes documentation from various sources, supports multiple document formats, and offers full-text search capabilities. It is designed for developers and AI assistants that need to retrieve documentation context via the MCP protocol, replicating Cursor’s @Docs functionality.

How to use Open Docs Mcp?

Run npx -y open-docs-mcp --docsDir ./docs to start the server. For Claude Desktop, add the server configuration to claude_desktop_config.json with the required --docsDir argument pointing to your documentation directory. Development commands include npm run watch for auto-rebuild and npm run inspector for debugging with MCP Inspector.

Key features of Open Docs Mcp

Crawls and indexes documentation from various sources
Supports multiple document formats (HTML, Markdown, etc.)
Full-text search with relevance scoring
Resource-based and tool-based MCP API
Automatic re-indexing to keep docs up-to-date

Use cases of Open Docs Mcp

Index documentation from external sources for AI context
Search across all indexed documentation using MCP tools
Add new documentation sources via the enable_doc tool
Force re-crawl of docs with crawl_docs tool
Manage enabled docs through list_enabled_docs

常见问题

What are the system requirements?

Node.js >= 16.0.0 and TypeScript 4.9.5 are required.

How do I configure Open Docs Mcp with Claude Desktop?

Add the server configuration to `~/Library/Application Support/Claude/claude_desktop_config.json` on macOS or `%APPDATA%/Claude/claude_desktop_config.json` on Windows, specifying `command`, `args` (including `--docsDir`), and optionally `disabled` and `alwaysAllow`.

What tools are available in Open Docs Mcp?

The server provides seven tools: `enable_doc`, `disable_doc`, `crawl_docs`, `build_index`, `search_docs`, `list_enabled_docs`, and `list_all_docs`.

How do I add a new documentation source?

Use the `enable_doc` tool to start crawling a specific documentation source.

Where does the indexed data live?

Data is stored in the directory specified by the `--docsDir` argument when starting the server.

记忆与知识分类下的更多 MCP 服务器

Leviathan Systems Public Content MCP

Leviathan Systems

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.

PLUR

plur-ai

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

226

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

Semantic Ui React

Semantic-Org

The official Semantic-UI-React integration

13.2K

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.