Happy slice of mcp pizzaMCP.pizza

google-research-mcp

MCP.Pizza Chef: zoharbabin

This server once let you search the web using Google Custom Search from your AI assistant, helping you find and verify information. It required developer setup and API keys. Now it is deprecated and replaced by web-researcher-mcp, which offers more search engines, better citation checks, and easier installation. If you want to do web research with your assistant, use the newer version instead.

Archived · The author made this repository read-only on GitHub.
Other
Web/Research

Use This MCP server To

Search the web for information from multiple search engines Verify citations and check for retracted sources Find academic papers, patents, and legal documents Cache search results securely for faster access Switch between search providers automatically if one fails

README

google-researcher-mcp — DEPRECATED

⚠️ This project has been superseded by web-researcher-mcp.

A complete rewrite in Go: same tools, but it cites real sources and stays honest — citation verification, retraction flagging, eight search providers behind one interface, and a single signed static binary. No Node.js, no npm.

Migrate in one line

Your API keys and tool calls don't change — only how the server is launched. Pick whichever you prefer (no Node required):

# macOS / Linux — installs the binary and registers it with Claude Code automatically:
curl -fsSL https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.sh | sh

# Windows (PowerShell):
powershell -ExecutionPolicy Bypass -c "irm https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.ps1 | iex"

# Python users (uv) — run with no install:
uvx web-researcher-mcp

Before / after (MCP client config)

The config keeps the same shape — swap the command/args, keep your env:

// BEFORE — google-researcher-mcp (npx / Node)
{
  "mcpServers": {
    "google-researcher": {
      "command": "npx",
      "args": ["-y", "google-researcher-mcp"],
      "env": { "GOOGLE_CUSTOM_SEARCH_API_KEY": "…", "GOOGLE_CUSTOM_SEARCH_ID": "…" }
    }
  }
}

// AFTER — web-researcher-mcp (installed binary; or use "uvx" + args ["web-researcher-mcp"])
{
  "mcpServers": {
    "web-researcher": {
      "command": "web-researcher-mcp",
      "env": { "GOOGLE_CUSTOM_SEARCH_API_KEY": "…", "GOOGLE_CUSTOM_SEARCH_ID": "…" }
    }
  }
}

Don't run both at once — they register identical tool names. Remove the google-researcher entry before adding web-researcher.

→ Full migration guide

Your existing GOOGLE_CUSTOM_SEARCH_API_KEY and GOOGLE_CUSTOM_SEARCH_ID work unchanged.

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 Eight providers (Brave, Serper, SearXNG, SearchAPI, Tavily, Exa, DuckDuckGo + Google PSE for lenses) with automatic fallback
#55 — Support alternative search engines Multiple engines behind one interface, plus a zero-config DuckDuckGo default
#72 — Add Redis caching Hybrid cache: memory + AES-encrypted disk + optional Redis
#40 — Split server.ts into modules Fully modular Go architecture (one package per concern)

Plus what's new: verify_citation and audit_bibliography (catch fabricated/retracted citations), academic / patent / SEC-filing / US-case-law / economic / clinical-trial search, and authority-weighted search lenses.

Links

google-research-mcp FAQ

Can I use this to perform web research with citation verification?
This version is deprecated; please use the newer web-researcher-mcp which supports citation verification and multiple search engines.
Does this server require API keys?
Yes, it uses your existing Google Custom Search API key and Search ID, which remain the same when migrating to the new version.
Can I run this on Windows or macOS?
The original requires developer setup like Docker or npx, but the new replacement offers easy install scripts for macOS, Linux, and Windows.
Is this compatible with Claude or other MCP clients?
It was designed for MCP clients but is now superseded by web-researcher-mcp, which works with Claude, Cursor, and others.
How hard is it to set up?
Setup is developer-level, needing Docker or command-line installs; the new version simplifies this.
Can I run both google-researcher-mcp and web-researcher-mcp at the same time?
No, they register identical tool names; remove the old before adding the new.