mcpField
G
google-researcher

google-researcher

Local
github.com/zoharbabinSearch36Updated 20w ago
Repository

About google-researcher

google-researcher is a deprecated MCP server offering Google Search, web scraping and multi-source research tools for AI assistants. Its successor, web-researcher-mcp, is a Go rewrite that keeps the same tools and API keys.

Key features

  1. 01Google Search and web scraping tools
  2. 02Multi-source research tools
  3. 03Successor written in Go as a single binary
  4. 04Existing Google Custom Search variables still work

Use cases

  1. 01Adding web search to AI assistants
  2. 02Migrating from the Node.js server to a standalone binary

MCP support

This is an MCP server that exposes search and research tools to MCP clients. The README advises switching to web-researcher-mcp and not running both, since they register identical tool names.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "zoharbabin-google-researcher": {
      "command": "npx",
      "args": [
        "-y",
        "google-researcher-mcp"
      ],
      "env": {
        "GOOGLE_CUSTOM_SEARCH_API_KEY": "<GOOGLE_CUSTOM_SEARCH_API_KEY>",
        "GOOGLE_CUSTOM_SEARCH_ID": "<GOOGLE_CUSTOM_SEARCH_ID>"
      }
    }
  }
}
Run commandnpx -y google-researcher-mcp
Environment variables to set
GOOGLE_CUSTOM_SEARCH_API_KEYSecretGoogle Custom Search API key
GOOGLE_CUSTOM_SEARCH_IDGoogle Programmable Search Engine ID

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmgoogle-researcher-mcp6.3.3

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project 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⚠️ This project has been superseded by web-researcher-mcp.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 IssueResolution in web-researcher-mcp
#108 — Orphan detection fails via npxGo binary has native process lifecycle (EOF/SIGPIPE) — no npm wrapper
#107 — Google discontinuing 'entire web' searchEight providers (Brave, Serper, SearXNG, SearchAPI, Tavily, Exa, DuckDuckGo + Google PSE for lenses) with automatic fallback
#55 — Support alternative search enginesMultiple engines behind one interface, plus a zero-config DuckDuckGo default
#72 — Add Redis cachingHybrid cache: memory + AES-encrypted disk + optional Redis
#40 — Split server.ts into modulesFully 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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.