Gemini DeepSearch

Performs automated multi-step web research using Google Search API and Gemini models to generate diverse search queries, conduct parallel searches, and synthesize comprehensive answers with proper source citations through configurable research depth levels.

This MCP server provides automated multi-step web research capabilities using Google Gemini models and Google Search API to perform deep information gathering with citation tracking. Built by Alex Cong using Python with LangGraph workflow orchestration, FastMCP integration, and Google's generative AI tools, it implements a sophisticated research agent that generates diverse search queries, conducts parallel web searches, reflects on knowledge gaps through iterative loops, and synthesizes final answers with proper source attribution. The implementation offers configurable effort levels (low/medium/high) that control research depth through query count and loop iterations, supports both HTTP API and stdio MCP deployment modes, and includes LangGraph Studio integration for workflow visualization, making it valuable for research tasks requiring comprehensive information synthesis, fact-checking with source verification, and scenarios where AI assistants need to gather current information beyond their training data through systematic web exploration.