Google Researcher MCP Server
About
Power your AI agents with Google Search–enhanced research via an open-source MCP server. Includes tools for Google Search, YouTube/web scraping, LLM-driven synthesis, persistent caching, and dual transport (STDIO + HTTP SSE) for efficient, flexible integration.
Details
- License
- MIT license
Explore
- Research Tools
- google_search: Find information via Google Search API
- scrape_page: Extract content from websites and YouTube videos
- analyze_with_gemini: Process text using Google's Gemini AI
- research_topic: Combine search, scraping, and analysis in one operation
- Performance & Reliability
- Persistent caching system (memory + disk)
- Session resumption for web clients
- Multiple transport options (STDIO, HTTP+SSE)
- Management API endpoints for monitoring and control
```bash
git clone <repository-url>
cd <repository-directory>
npm install
cp .env.example .env
google_search
Search the web
scrape_page
Extract content from URLs
analyze_with_gemini
Process text with AI
research_topic
Combined research workflow
| Tool | Description | Parameters |
|------|-------------|------------|
| google_search | Search the web | query (string), num_results (number, default: 5) |
| scrape_page | Extract content from URLs | url (string) |
| analyze_with_gemini | Process text with AI | text (string), model (string, default: "gemini-2.0-flash-001") |
| research_topic | Combined research workflow | query (string), num_results (number, default: 3) |
> Empower AI assistants with web research capabilities through Google Search, content scraping, and Gemini AI analysis.
This server implements the Model Context Protocol (MCP), allowing AI clients to perform research tasks with persistent caching for improved performance and reduced API costs.
Quick Start
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
