MCP Server

Maintained

MIT

io.github.zoharbabin/google-researcher MCP Server

io.github.zoharbabin/google-researcher

Deprecated Node.js research server; migrate to web-researcher-mcp for multi-source search with citation verification.

What is the io.github.zoharbabin/google-researcher MCP server?

The google-researcher-mcp server is a deprecated MCP tool that provided Google Search and web scraping capabilities for AI assistants. It has been superseded by web-researcher-mcp, a Go-based rewrite offering the same API with citation verification, multiple search providers, and improved reliability.

This server enabled AI assistants to perform web research and scraping via Google Search. It is now deprecated in favor of web-researcher-mcp, which provides identical tool interfaces but with a native Go binary, support for eight search engines (Brave, Serper, SearXNG, SearchAPI, Tavily, Exa, DuckDuckGo, Google PSE), citation verification, and caching. Existing API keys and tool calls remain compatible during migration.

How to install io.github.zoharbabin/google-researcher

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

GOOGLE_CUSTOM_SEARCH_API_KEY
required
secret
Google Custom Search API key
GOOGLE_CUSTOM_SEARCH_ID
required
Google Programmable Search Engine ID

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "google-researcher": {
      "command": "node",
      "args": [
        "-y",
        "google-researcher-mcp"
      ],
      "env": {
        "GOOGLE_CUSTOM_SEARCH_API_KEY": "<YOUR_GOOGLE_CUSTOM_SEARCH_API_KEY>",
        "GOOGLE_CUSTOM_SEARCH_ID": "<YOUR_GOOGLE_CUSTOM_SEARCH_ID>"
      }
    }
  }
}

Use cases

Perform web searches and retrieve results for research tasks
Scrape and extract content from web pages
Verify citations and detect fabricated or retracted sources
Access multiple search engines through a unified interface
Cache search results for improved performance

io.github.zoharbabin/google-researcher MCP server FAQ

What is google-researcher-mcp?

A deprecated MCP server that provided Google Search and web scraping for AI assistants. It has been replaced by web-researcher-mcp, which offers the same tools with better reliability and citation verification.

Should I use this server?

No. The project is deprecated. Migrate to web-researcher-mcp instead—it uses the same API keys and tool calls but runs as a native Go binary with more features and no Node.js dependency.

How do I migrate from google-researcher-mcp?

Update your MCP client config to use the web-researcher-mcp command instead of npx google-researcher-mcp. Your GOOGLE_CUSTOM_SEARCH_API_KEY and GOOGLE_CUSTOM_SEARCH_ID remain unchanged. See the migration guide at https://github.com/zoharbabin/web-researcher-mcp/blob/main/docs/MIGRATION.md.

What authentication is required?

GOOGLE_CUSTOM_SEARCH_API_KEY and GOOGLE_CUSTOM_SEARCH_ID for Google search, or API keys for alternative providers (Brave, Serper, Tavily, etc.) in the successor web-researcher-mcp.

Is this free?

The server itself is open-source. Search provider costs depend on your chosen backend (Google Custom Search, Brave, Serper, etc.).

Why was this deprecated?

The rewrite in Go fixes process lifecycle issues, adds support for eight search engines as Google discontinues 'entire web' search, includes citation verification, and eliminates the Node.js/npm dependency.

README (reference)

Source of truth, from the repository.

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.

Related MCP servers

Web Researcher MCP

Active

AI research assistant that cites real sources—search trusted sites, read full articles, verify citations, never hallucinate.

MIT

View repository →

io.github.zoharbabin/brand-voice

Maintained

Enforce brand writing guidelines in Claude Code — PostToolUse hook + MCP server

TypeScript

MIT

View repository →

io.github.zombico/mojulo

Active

A 3D compiler for coding agents: objects, worlds and games as small recipes. Emits Godot and STL.

JavaScript

Apache-2.0

View repository →

QuantContext

Maintained

Deterministic stock screening, backtesting, and factor analysis for AI trading agents using real market data.

Python

MIT

View repository →

io.github.zoom/zoom-docs

Maintained

Zoom Docs server for creating and retrieving Zoom documents and notes in Markdown.

MIT

View repository →

io.github.zoom/zoom-meetings

Maintained

Zoom Meetings server for meeting search, recordings, transcripts, summaries, and meeting assets.

MIT

View repository →

io.github.zoharbabin/google-researcher MCP Server

What is the io.github.zoharbabin/google-researcher MCP server?

How to install io.github.zoharbabin/google-researcher

Use cases

io.github.zoharbabin/google-researcher MCP server FAQ

google-researcher-mcp — DEPRECATED

Migrate in one line

Before / after (MCP client config)

Why the Rewrite?

Links

Related MCP servers

Web Researcher MCP

io.github.zoharbabin/brand-voice

io.github.zombico/mojulo

QuantContext

io.github.zoom/zoom-docs

io.github.zoom/zoom-meetings