Google Researcher MCP
This server provides a comprehensive suite of web research tools combining Google-powered search, content extraction, and specialized discovery capabilities.
Web Search: Search the web via Google Custom Search API, returning URLs, titles, and snippets. Supports filtering by country, language, time range, exact phrases, site restrictions, and safe search.
Page Scraping: Extract text from any URL — including static and JavaScript-rendered pages, YouTube videos (via transcripts), and documents (PDF, DOCX, PPTX). Includes a preview mode to inspect page structure before full retrieval.
Search & Scrape Combined: Perform a Google search and automatically retrieve content from top results in a single call, returning deduplicated, combined content with source attribution — ideal for multi-source research.
Image Search: Find images with filters for size, type (photo, clipart, face, lineart, animated), color type, dominant color, and file format.
News Search: Discover recent news articles with freshness filters (hour/day/week/month/year), sorting by relevance or date, and optional restriction to a specific news source domain.
Academic Paper Search: Search peer-reviewed papers from arXiv, PubMed, IEEE, Nature, Springer, and more. Returns abstracts, authors, publication years, PDF links, and pre-formatted citations (APA, MLA, BibTeX).
Patent Search: Research patents via Google Patents with filters for assignee, inventor, CPC code, patent office (USPTO, EPO, WIPO, etc.), and date range. Supports prior art discovery and technology landscape analysis.
Sequential Research Tracking: Manage complex, multi-step research sessions across multiple API calls, supporting branching paths, knowledge gap identification, revision of earlier steps, and session persistence.
Provides academic paper search capabilities through the arXiv repository, enabling AI assistants to find research papers with citation formats (APA, MLA, BibTeX), abstracts, and PDF links.
Enables web search capabilities via Google Custom Search API, providing general web search with site, date, and language filtering for research and information gathering.
Provides news search functionality through Google News, allowing AI assistants to find current news articles with freshness controls and date sorting.
Enables academic paper search through IEEE repositories, providing access to peer-reviewed technical papers and research publications.
Provides biomedical and life sciences paper search capabilities through PubMed, enabling access to medical research articles and scientific publications.
Enables academic paper search through Springer repositories, providing access to scientific and technical research publications.
Provides automatic transcript extraction from YouTube videos, enabling AI assistants to access and analyze video content through text transcripts.
google-researcher-mcp — DEPRECATED
⚠️ This project has been superseded by
web-researcher-mcp.The new version is a complete rewrite in Go that resolves all open issues, adds multiple search providers (Brave, Serper, SearXNG), and ships as a single static binary — no Node.js or npm required.
Migration Guide
Quick summary:
Remove the
google-researcherentry from your MCP client configInstall the new binary (
go install, Docker, or download from Releases)Add the
web-researcherentry to your MCP config
Your existing GOOGLE_CUSTOM_SEARCH_API_KEY and GOOGLE_CUSTOM_SEARCH_ID work without changes.
Why the Rewrite?
Open Issue | Resolution in web-researcher-mcp |
#108 — Orphan detection fails via npx | Go binary has native process lifecycle (EOF/SIGPIPE) — no npm wrapper |
#107 — Google discontinuing 'entire web' search | Supports 4 providers: Brave, Serper, SearXNG + Google PSE for lenses |
#55 — Support alternative search engines | Built-in Brave, Serper, and SearXNG support |
#72 — Add Redis caching | Hybrid 3-tier cache: memory + AES-encrypted disk + optional Redis |
#40 — Split server.ts into modules | Fully modular Go architecture (one package per concern) |
Links
New project: https://github.com/zoharbabin/web-researcher-mcp
Docker:
docker pull zoharbabin/web-researcher-mcp:latestReleases: https://github.com/zoharbabin/web-researcher-mcp/releases
This repository is archived and read-only. No further updates will be made here.
Maintenance
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/zoharbabin/google-researcher-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server