Deep Research

A Model Context Protocol (MCP) compliant server designed for comprehensive web research. It uses Tavily's Search and Crawl APIs to gather detailed information on a given topic, then structures this data in a format perfect for LLMs to create high-quality markdown documents.

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": {
    "pinkpixel-dev-deep-research-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@pinkpixel/deep-research-mcp"
      ],
      "env": {
        "CRAWL_LIMIT": "15",
        "CRAWL_TIMEOUT": "300",
        "SEARCH_TIMEOUT": "120",
        "TAVILY_API_KEY": "tvly-YOUR_ACTUAL_API_KEY_HERE",
        "CRAWL_MAX_DEPTH": "2",
        "FILE_WRITE_ENABLED": "true",
        "MAX_SEARCH_RESULTS": "10",
        "ALLOWED_WRITE_PATHS": "/home/user/research,/home/user/documents",
        "DOCUMENTATION_PROMPT": "Generate a detailed technical whitepaper with abstract, sections, and diagrams.",
        "FILE_WRITE_LINE_LIMIT": "500"
      }
    }
  }
}

The Deep Research MCP Server is a Model Context Protocol (MCP) compliant server that performs thorough web research using Tavily's Search and Crawl APIs. It aggregates results and generates structured guidance for large language models to produce high-quality markdown documentation.

How to use

You use this MCP server by connecting an MCP client and issuing a tool call to the deep-research-tool with your research query. The server then searches the web, crawls relevant sources, and returns a structured JSON body that includes a comprehensive prompt for how to generate markdown documentation, a summary of the search, and the detailed findings from each crawled source. Your client should then pass that structured data to your language model to produce the final Markdown document.

Key practical outcomes you can achieve include: preparing up-to-date technical documentation from diverse sources, saving generated content and assets to a configured path, and tailoring the final output with a custom documentation prompt when needed.

How to install

Prerequisites you need before installation:

Node.js (version 18.x or later recommended)
npm
Yarn

Choose one of the installation methods below.

Option A: Quick run with NPX (recommended for quick use)

npx @pinkpixel/deep-research-mcp

Option B: Temporary execution via NPX (no global install)

npx @pinkpixel/deep-research-mcp

Option C: Global installation (optional)

Install globally so you can run the server from anywhere.

npm install -g @pinkpixel/deep-research-mcp

Then start it with:

deep-research-mcp

## Option D: Local project integration or development

If you want to modify or contribute, set up a local development environment.

git clone https://github.com/your-username/deep-research-mcp.git cd deep-research-mcp npm install


## Available tools

### write-research-file

Tool to save research findings to files with controlled access and safety measures.

### deep-research-tool

Primary MCP tool that conducts Tavily search, crawl, and data aggregation for document generation.

Built by

VeilStrat

AI signals for GTM teams