Deep Research

MCP Deep Research is a tool that allows you to search the web for information. It is built with the Model Context Protocol and the Tavily API.

javascript

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "baranwang-mcp-deep-research": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-deep-research@latest"
      ],
      "env": {
        "TAVILY_API_KEY": "YOUR_TAVILY_API_KEY",
        "TAVILY_HTTP_PROXY": "http://proxy:port",
        "TAVILY_HTTPS_PROXY": "https://proxy:port",
        "MAX_PLANNING_ROUNDS": "5",
        "MAX_SEARCH_KEYWORDS": "5"
      }
    }
  }
}

MCP Deep Research lets you search the web for information through an MCP client, powered by the Model Context Protocol and the Tavily API. It enables you to perform targeted web queries and plan subsequent actions based on results, all within an MCP workflow.

How to use

You connect to this MCP server from a compatible MCP client and issue information-seeking prompts. It leverages the Tavily-backed search and planning flow to collect data from the web and return structured results you can use in follow-up steps. Use it when you need up-to-date web information integrated into your MCP conversations.

How to install

Prerequisites you need before installing this MCP server: Node.js installed on your system and npm available in your command shell.

# Optional: install via Smithery for Claude Desktop client compatibility
npx -y @smithery/cli install @baranwang/mcp-deep-research --client claude

Configuration and startup

Configure the MCP server to run with the following command and arguments. The server requires a Tavily API key and supports optional limits for keywords and planning rounds.

{
  "mcpServers": {
    "deep_research": {
      "command": "npx",
      "args": ["-y", "mcp-deep-research@latest"],
      "env": {
        "TAVILY_API_KEY": "your_tavily_api_key",
        "MAX_SEARCH_KEYWORDS": "5",
        "MAX_PLANNING_ROUNDS": "5"
      }
    }
  }
}

Notes on usage and security

Keep your Tavily API key secure. Do not expose it in public scripts or logs. If you operate behind a proxy, you can provide proxy details via the environment variables described in the configuration section.

Built by

VeilStrat

AI signals for GTM teams