We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, to analyze how the site is used.

You can freely give, refuse or withdraw your consent at any time.

Google AI Search

MCP server by shariqriazz

Run web-grounded search, documentation lookups, code analysis and architecture research through Google Vertex AI or the Gemini API.

Runs locally (Runs on your machine: its page has the install command)Runs with npxNeeds an API key

Runs on your machine. Your client starts it with this command:

npx -y google-ai-search-mcp

Needs Node.js on your computer. The setup steps below show where the command goes in each client.

  • AI_PROVIDER optional Select vertex or gemini. Defaults to vertex.
  • GOOGLE_CLOUD_PROJECT optional Google Cloud project ID. Required when AI_PROVIDER is vertex.
  • GOOGLE_CLOUD_LOCATION optional Vertex AI location. Defaults to us-central1.
  • GEMINI_API_KEY secret optional Gemini API key. Required when AI_PROVIDER is gemini.

Share this server

Opens this page, with the install command and setup steps.

mcp.tc/i/google-ai-search

A community MCP server that exposes Google AI models (Vertex AI or the Gemini API) as developer-focused tools. It answers queries with web search grounding, explains topics from official documentation, retrieves doc snippets, generates project guidelines, analyzes code against documentation, compares technologies and recommends architecture patterns.

It runs locally over stdio from the npm package google-ai-search-mcp, started with npx or bunx. Set AI_PROVIDER to vertex (needs GOOGLE_CLOUD_PROJECT and Google Cloud credentials) or gemini (needs GEMINI_API_KEY). Output is model-generated and should be checked against primary sources.

  • Answer technical queries using Google AI with web search grounding
  • Explain topics using official documentation
  • Retrieve code snippets from official docs
  • Generate structured project guidelines for a technology stack
  • Analyze code against documentation best practices
  • Compare technologies across given criteria
  • Recommend architecture patterns with tradeoffs

Google AI Search lists its tools only to clients with a key, so we can’t show them here.

  • Search the web for the latest breaking changes in Next.js and summarize them

  • Explain how Kubernetes network policies work, using the official docs

  • Get code snippets for using the Gemini API streaming endpoint

  • Compare Postgres and MongoDB for an event logging workload

Every client starts Google AI Search on your machine with the same command. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport stdio google-ai-search --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" -- npx -y google-ai-search-mcp
  1. Start Claude Code and type /mcp. google-ai-search should show as connected.

Add --scope user to make it available in every project. Replace the placeholders with your own values.

Claude Desktop

  1. Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:
claude_desktop_config.json
{
  "mcpServers": {
    "google-ai-search": {
      "command": "npx",
      "args": [
        "-y",
        "google-ai-search-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
      }
    }
  }
}
  1. Save the file and restart Claude Desktop. Replace the placeholders with your own values.

Needs Node.js on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "google-ai-search": {
      "command": "npx",
      "args": [
        "-y",
        "google-ai-search-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
      }
    }
  }
}

Needs Node.js on your computer. Replace the placeholders with your own values.

VS Code

Add it to .vscode/mcp.json. VS Code asks for the secret the first time and stores it securely:

.vscode/mcp.json
{
  "servers": {
    "google-ai-search": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "google-ai-search-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "${input:gemini-api-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "gemini-api-key",
      "description": "GEMINI_API_KEY",
      "password": true
    }
  ]
}

Needs Node.js on your computer.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "google-ai-search": {
      "command": "npx",
      "args": [
        "-y",
        "google-ai-search-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
      }
    }
  }
}
  1. Refresh the MCP server list in Cascade. Replace the placeholders with your own values.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add google-ai-search --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" -- npx -y google-ai-search-mcp

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.google-ai-search]
command = "npx"
args = ["-y", "google-ai-search-mcp"]
env = { GEMINI_API_KEY = "<YOUR_GEMINI_API_KEY>" }

Needs Node.js on your computer. Replace the placeholders with your own values.

Gemini CLI

gemini mcp add -e "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" google-ai-search npx -- -y google-ai-search-mcp

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

{
  "mcpServers": {
    "google-ai-search": {
      "command": "npx",
      "args": [
        "-y",
        "google-ai-search-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
      }
    }
  }
}

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs Node.js on your computer. Replace the placeholders with your own values.

Show Google AI Search in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

This server runs on your computer, so we follow its npm package: each new version shows up here, with edits by its owner.

Follow Google AI Search and we’ll email you when something changes.

  1. , Automatic check

    Tracking started: version 1.1.1.

Can I paste mcp.tc/i/google-ai-search into my MCP client?

No. Google AI Search runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is npx -y google-ai-search-mcp.

Does Google AI Search need an API key?

Yes. It reads GEMINI_API_KEY from its environment, and GEMINI_API_KEY is a secret. Put the value in your client’s config on your own machine, never in a shared file.

Is Google AI Search a remote or a local server?

Local. Your client starts it as a process on your computer with npx -y google-ai-search-mcp, which needs Node.js.

What can Google AI Search do?

You can answer technical queries using Google AI with web search grounding, explain topics using official documentation and retrieve code snippets from official docs.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Does mcp.tc track changes to Google AI Search?

Partly. It runs on your computer, so we follow its npm package: its History tab shows each new version and edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read Google AI Search’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with shariqriazz. This page was built from Google AI Search’s public metadata, last checked on 4 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.