# Google AI Search MCP

This MCP server gives AI coding clients Google AI web search and documentation tools. Use it when answers need current technical sources.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 7
- Author: shariqriazz
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/shariqriazz/google-ai-search-mcp
- Updated: 2026-09-07
- HTML: https://affpapa.org/en/nevibecode/mcp/google-ai-search-mcp

## What it does

Google AI Search MCP connects MCP clients to tools backed by Vertex AI or the Gemini API. It can retrieve current web information, explain technical subjects from official documentation, find code snippets, and draft project guidance.

The server also offers code review against documented practices, technology comparisons, and architecture options for a described use case. Environment variables control the provider, model, temperature, streaming, output-token limit, and retry behavior. Treat generated comparisons and architecture advice as material to verify against primary sources.

You need Node.js v18+, Bun, and credentials for a provider. Vertex AI requires a billed Google Cloud Project, the Vertex AI API, and Google Cloud authentication; Gemini requires `GEMINI_API_KEY`. Without a configured provider, the server cannot call the model.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `AI_PROVIDER`, `GOOGLE_CLOUD_PROJECT`, `GOOGLE_CLOUD_LOCATION`, `GEMINI_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env AI_PROVIDER=<AI_PROVIDER> --env GOOGLE_CLOUD_PROJECT=<GOOGLE_CLOUD_PROJECT> --env GOOGLE_CLOUD_LOCATION=<GOOGLE_CLOUD_LOCATION> --env GEMINI_API_KEY=<GEMINI_API_KEY> --transport stdio google-ai-search-mcp -- npx -y google-ai-search-mcp
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add google-ai-search-mcp --env AI_PROVIDER=<AI_PROVIDER> --env GOOGLE_CLOUD_PROJECT=<GOOGLE_CLOUD_PROJECT> --env GOOGLE_CLOUD_LOCATION=<GOOGLE_CLOUD_LOCATION> --env GEMINI_API_KEY=<GEMINI_API_KEY> -- npx -y google-ai-search-mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "google-ai-search-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "google-ai-search-mcp"
            ],
            "env": {
                "AI_PROVIDER": "<AI_PROVIDER>",
                "GOOGLE_CLOUD_PROJECT": "<GOOGLE_CLOUD_PROJECT>",
                "GOOGLE_CLOUD_LOCATION": "<GOOGLE_CLOUD_LOCATION>",
                "GEMINI_API_KEY": "<GEMINI_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "google-ai-search-mcp": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "google-ai-search-mcp"
            ],
            "env": {
                "AI_PROVIDER": "<AI_PROVIDER>",
                "GOOGLE_CLOUD_PROJECT": "<GOOGLE_CLOUD_PROJECT>",
                "GOOGLE_CLOUD_LOCATION": "<GOOGLE_CLOUD_LOCATION>",
                "GEMINI_API_KEY": "<GEMINI_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e AI_PROVIDER=<AI_PROVIDER> -e GOOGLE_CLOUD_PROJECT=<GOOGLE_CLOUD_PROJECT> -e GOOGLE_CLOUD_LOCATION=<GOOGLE_CLOUD_LOCATION> -e GEMINI_API_KEY=<GEMINI_API_KEY> google-ai-search-mcp npx -y google-ai-search-mcp
```
Replace <…> with your own values

## When to use it
- retrieve current answers about a library
- explain a topic from official documentation
- find a version-specific code snippet
- compare technologies using chosen criteria
- review code against documented practices

## Example prompts
- Use `answer_query_websearch` to find the current authentication setup for this library.
- Use `explain_topic_with_docs` to explain this error from official documentation.
- Use `technical_comparison` to compare `technology-a` and `technology-b` by cost and constraints.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md