Deep Search

The Deep Search MCP Server delivers comprehensive deep search capabilities through a production-ready MCP interface. It enables web search, content extraction, multi-source research with summaries, and access to news and academic content, all via a unified MCP endpoint for your AI assistant workflows.

How to use

Connect your MCP client to the Deep Search MCP Server to enable powerful search and research capabilities within your AI assistant. You can query web results, extract readable content from URLs, perform multi-source deep research with summaries, and retrieve recent news and academic papers. Use the server to empower your assistant with up-to-date information from multiple data sources.

How to install

Prerequisites you need before installation.

• Node.js 20+ must be installed on your system
• npm, yarn, or pnpm should be available to manage dependencies

Step-by-step installation flow.

• Clone the project repository:

# Clone the repository
git clone https://github.com/LikhonSheikh404/deep-search-mcp.git
cd deep-search-mcp

# Install dependencies
npm install

# Copy environment file
cp .env.example .env

# Start development server
npm run dev

Configuration and testing notes

To connect your MCP client, point it at the server endpoint exposed by the running Deep Search MCP Server. The server exposes an HTTP MCP endpoint that your client can call to perform web search, content extraction, and multi-source research.

{
  "mcpServers": {
    "deep_search": {
      "url": "https://deep-search-mcp.vercel.app/api/mcp"
    }
  }
}

Available tools

web_search

Search the web for information with a query and optional max results.

extract_content

Extract readable content from a given URL.

deep_research

Perform multi-source research with a depth parameter and provide summaries.

news_search

Find recent news articles related to a topic.

academic_search

Search for academic papers and scholarly content.