google-researcher-mcp
by zoharbabin·★ 35·Score 46
MCP server providing Google search, web scraping, and document parsing with advanced filtering capabilities.
Overview
Google Researcher MCP Server is a comprehensive tool for AI assistants that enables web search, content extraction, and research capabilities. It supports Google search (general, news, images), webpage scraping including JavaScript-rendered sites, YouTube transcript extraction, and document parsing (PDF, DOCX, PPTX). The server features quality scoring, caching mechanisms, and enterprise-grade security with OAuth support. It's designed for production use with multiple transport options and is actively maintained.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose this when you need comprehensive web research capabilities including Google search, news, academic papers, patents, and document parsing in a single MCP server.
When NOT to choose this
Avoid if you need to bypass Google's search restrictions or require functionality beyond what Google APIs provide, as this is tied to Google's services.
Tools this server exposes
8 tools extracted from the READMEgoogle_search(query: string, num_results?: number, time_range?: string, site_search?: string, exact_terms?: string, exclude_terms?: string) => Promise<any>Web search with site, date, and language filters
google_news_search(query: string, num_results?: number, freshness?: string, sort_by?: string, news_source?: string) => Promise<any>News search with freshness controls
google_image_search(query: string, num_results?: number, size?: string, type?: string, color_type?: string, file_type?: string) => Promise<any>Image search with type, size, color filters
scrape_page(url: string) => Promise<any>Extract content from web pages, PDFs, DOCX and YouTube transcripts
search_and_scrape(query: string, num_results?: number, include_sources?: boolean, deduplicate?: boolean, max_length_per_source?: number, total_max_length?: number, filter_by_query?: boolean) => Promise<any>Combined search + content extraction with quality scoring
academic_search(query: string, num_results?: number) => Promise<any>Search for academic papers from arXiv, PubMed, IEEE with citations
patent_search(query: string, search_type?: string) => Promise<any>Patent search with assignee/inventor filters for prior art analysis
sequential_search(searchStep: string, stepNumber: number, totalStepsEstimate?: number, nextStepNeeded?: boolean) => Promise<any>Multi-step research tracking with state management
Comparable tools
Installation
Installation
Claude Desktop (macOS)
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"google-researcher": {
"command": "npx",
"args": ["-y", "google-researcher-mcp"],
"env": {
"GOOGLE_CUSTOM_SEARCH_API_KEY": "YOUR_API_KEY_HERE",
"GOOGLE_CUSTOM_SEARCH_ID": "YOUR_SEARCH_ID_HERE"
}
}
}
}Claude Desktop (Windows)
Add to %APPDATA%\Claude\claude_desktop_config.json with the same configuration.
FAQ
- What API keys are required?
- You need a Google Custom Search API key and Search ID. See the API Setup Guide for step-by-step instructions.
- Which clients are supported?
- This MCP server supports Claude Desktop, Claude Code, Cursor, and any MCP client that supports STDIO transport.
Compare google-researcher-mcp with
Last updated · Auto-generated from public README + GitHub signals.