Docsearch Mcp

Created By

PatrickKoss2 months ago

ripgrep for docs but via MCP

Overview

What is Docsearch MCP?

Docsearch MCP is a local-first document search and indexing system that provides hybrid semantic and keyword search across local files (including PDFs) and Confluence pages through the Model Context Protocol (MCP). It is designed to assist AI tools in accessing documentation, codebases, and research materials.

How to use Docsearch MCP?

To use Docsearch MCP, you can install it via npm or run it using Docker. After installation, you can index your documents and search through them using the command-line interface (CLI).

Key features of Docsearch MCP?

Hybrid Search: Combines full-text search with vector similarity for optimal results.
Multi-Source Indexing: Index local files and Confluence spaces.
PDF Support: Extract and search text from PDF documents.
Image Search: AI-powered image description and search.
Database Flexibility: Supports SQLite and PostgreSQL.
Real-time Updates: Automatic re-indexing with file watching.
Multiple Output Formats: Supports text, JSON, and YAML outputs.

Use cases of Docsearch MCP?

Searching through code documentation.
Indexing and searching academic papers.
Assisting AI tools in retrieving relevant documentation.

FAQ from Docsearch MCP?

Can Docsearch MCP index all file types?

Yes, it supports various file types including code files, PDFs, and images.

Is Docsearch MCP free to use?

Yes, it is open-source and free to use.

How does the hybrid search work?

It combines traditional keyword search with semantic search using vector embeddings.

Server Config

{
  "mcpServers": {
    "docsearch": {
      "command": "npx",
      "args": [
        "docsearch-mcp",
        "start"
      ],
      "env": {
        "OPENAI_API_KEY": "your-openai-key",
        "EMBEDDINGS_PROVIDER": "openai",
        "FILE_ROOTS": ".,../other-project",
        "DB_PATH": "/path/to/your/index.db"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code

TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

DeepChatYour AI Partner on Desktop

WindsurfThe new purpose-built IDE to harness magic

EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

Serper MCP ServerA Serper MCP Server

MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.