deep-research-mcp

deep-research-mcp

3.4

If you are the rightful owner of deep-research-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Deep Research MCP Server is a Model Context Protocol compliant server designed for comprehensive web research, leveraging Tavily's Search and Crawl APIs to gather and structure data for LLMs.

The Deep Research MCP Server is a powerful tool designed to perform extensive web research by utilizing Tavily's Search and Crawl APIs. It aggregates data into a structured JSON format, optimized for Large Language Models (LLMs) to generate detailed markdown documents. The server is MCP compliant, making it an ideal component for AI agent ecosystems. It offers multi-step research capabilities, structured JSON output, and configurable documentation prompts and output paths. The server is designed to integrate seamlessly into MCP-based AI agent ecosystems, providing granular control over search and crawl processes.

Features

  • Multi-Step Research: Combines Tavily's AI-powered web search with deep content crawling for thorough information gathering.
  • Structured JSON Output: Provides well-organized data optimized for LLM consumption.
  • Configurable Documentation Prompt: Includes a comprehensive default prompt for generating high-quality technical documentation, which can be overridden.
  • Configurable Output Path: Allows specification of where research documents and images should be saved.
  • Granular Control: Offers a wide range of parameters to fine-tune both the search and crawl processes.