gsearch

io.github.RayenMlayeh/gsearch

Real Google Search for AI agents: real URLs, AI Overview and People also ask as typed JSON.

View repository →

Connect this server

Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.

{
  "mcpServers": {
    "gsearch": {
      "command": "uvx",
      "args": [
        "gsearch-agent"
      ],
      "env": {
        "GSEARCH_PROXY": "<your GSEARCH_PROXY>"
      }
    }
  }
}
Environment variables
  • GSEARCH_PROXYsecretOptional proxies in any format (host:port:user:pass, user:pass@host:port, socks5://...), or a file listing them. Unset: your own IP, at most 20 searches an hour.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
AI & ML
Version
0.1.0
Registry
active
Published
10/18/2026

More AI & ML servers

Browse all AI & ML →

io.github.Rckl88/clawbackai-mcp

Rckl88

LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.

AI & MLAdded 7 months ago

FirstAGI Arena

realbtr

Scored research challenges for AI agent fleets on a non-LLM cognitive architecture.

AI & MLAdded 1 week ago

io.github.replynodes/mcp

replynodes

Connect AI agents to Replynodes over the Model Context Protocol.

AI & MLAdded 2 months ago

io.github.retain-so/mcp-server

retain-so

Model Context Protocol server for Retain: let AI agents query churn risk and act on retention.

AI & MLAdded 5 months ago

Losbeto — Market Data for AI Agents

rmartins1451

Cross-asset market data, LLM gateway and ML forecasts for AI agents. USDC via x402 + MPP.

AI & MLAdded 2 days ago

io.github.rog0x/web

rog0x

Web scraping, search, monitoring, and HTML-to-markdown for AI agents

AI & MLAdded 7 months ago

Add the badge to your site

Show visitors that gsearch is listed here — it’s also the link we check for a free listing.

gsearch — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-rayenmlayeh-gsearch?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="gsearch — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![gsearch — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-rayenmlayeh-gsearch?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.