google-research-mcp
1
The Google Researcher MCP Server enhances AI assistants with advanced web research functionality, utilizing tools like Google Search and Gemini AI for content analysis. This open-source project offers robust performance with features like persistent caching and flexible integration options.
Google Researcher MCP Server
Empower AI assistants with web research capabilities through Google Search, content scraping, and Gemini AI analysis.
Features
- Research Tools
- google_search: Find information via Google Search API
- scrape_page: Extract content from websites
- analyze_with_gemini: Process text using Google's Gemini AI
- research_topic: Combine search, scraping, and analysis
- Performance & Reliability
- Persistent caching system
- Session resumption for web clients
- Multiple transport options
- Management API endpoints for control
Why Use This?
- Extend AI Capabilities with real-time web information
- Save Money with caching
- Improve Performance on repeated queries
- Flexible Integration with MCP-compatible clients
Installation
- Requires Node.js v18+
- API Keys: Google Custom Search API, Google Custom Search Engine ID, Google Gemini API
Usage
- Available Tools: google_search, scrape_page, analyze_with_gemini, research_topic
Architecture
- Transport Layer: STDIO and HTTP+SSE
- MCP Core: Request handling
- Tools Layer: Research capabilities
- Support Systems: Caching and event store
Contributing
- Star the repo
- Fork to create your version
- Submit PRs for improvements
License
MIT Licensed