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.
Install Google AI Search
Runs on your machine. Your client starts it with this command:
Needs Node.js on your computer. The setup steps below show where the command goes in each client.
AI_PROVIDERoptional Select vertex or gemini. Defaults to vertex.GOOGLE_CLOUD_PROJECToptional Google Cloud project ID. Required when AI_PROVIDER is vertex.GOOGLE_CLOUD_LOCATIONoptional Vertex AI location. Defaults to us-central1.GEMINI_API_KEYsecret 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-searchAbout
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.
What you can do
- 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
Tools
Google AI Search lists its tools only to clients with a key, so we can’t show them here.
Example prompts
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
Set up
Every client starts Google AI Search on your machine with the same command. Pick yours; the page remembers your choice.
Claude Code
- 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- 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
- Open Settings → Developer → Edit Config. It opens
claude_desktop_config.json. Add:
{
"mcpServers": {
"google-ai-search": {
"command": "npx",
"args": [
"-y",
"google-ai-search-mcp"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
}
}
}
}- 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
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"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:
{
"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
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"google-ai-search": {
"command": "npx",
"args": [
"-y",
"google-ai-search-mcp"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
}
}
}
}- 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-mcpOr edit ~/.codex/config.toml directly:
[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-mcpThis 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.
Embed
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.
README badge
[](https://mcp.tc/i/google-ai-search)<a href="https://mcp.tc/i/google-ai-search"><img src="https://mcp.tc/i/google-ai-search/badge.svg" alt="Google AI Search on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/google-ai-search.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/google-ai-search" title="Google AI Search on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/google-ai-search.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Google AI Search card to your site.
Add the mcp.tc card for Google AI Search, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/google-ai-search.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="google-ai-search"><a href="https://mcp.tc/i/google-ai-search">Google AI Search on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/google-ai-search)
```
Reference: https://mcp.tc/embedChange history
This server runs on your computer, so we follow its npm package: each new version shows up here, with edits by its owner.
FAQ
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.