Gemini Google SearchSAFE
MCP server for Google Search integration using Gemini's built-in search capabilities
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
日本語
A Model Context Protocol (MCP) server that provides Google Search functionality using Gemini's built-in Grounding with Google Search feature.
This project is inspired by the GoogleSearch tool from gemini-cli.
Features
- Uses Gemini's built-in Grounding with Google Search feature
- Provides real-time web search results with source citations
- Compliant with MCP standard protocol
- Supports stdio transport
- Supports both Google AI Studio and Vertex AI
Requirements
- Node.js 18 or later
- Google AI Studio API key (Get one here) or Google Cloud Project with Vertex AI enabled
Installation
npm install -g mcp-gemini-google-search
Usage
Environment Variables
# For Google AI Studio (default) export GEMINI_API_KEY="your-api-key-here" export GEMINI_MODEL="gemini-2.5-flash" # Optional (default: gemini-2.5-flash) # For Vertex AI export GEMINI_PROVIDER="vertex" export VERTEX_PROJECT_ID="your-gcp-project-id" export VERTEX_LOCATION="us-central1" # Optional (default: us-central1) export GEMINI_MODEL="gemini-2.5-flash" # Optional (default: gemini-2.5-flash)
Claude Code Configuration
You can set up this MCP server in Claude Code using the CLI:
For Google AI Studio
# Add to user scope (available across all projects) claude mcp add gemini-google-search \ -s user \ -e GEMINI_API_KEY="your-api-key-here" \ -e GEMINI_MODEL="gemini-2.5-flash" \ -- npx mcp-gemini-google-search # Or add to project scope to share with your team claude mcp add gemini-google-search \ -s project \ -e GEMINI_API_KEY="your-api-key-here" \ -e GEMINI_MODEL="gemini-2.5-flash" \ -- npx mcp-ge
23392b073693OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-gemini-google-search --env GEMINI_API_KEY=${GEMINI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"mcp-gemini-google-search": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
google_search | read | Performs a web search using Google Search (via the Gemini API) and returns the results. This tool is useful for finding information on the internet based on a query. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@google/genai, @modelcontextprotocol/sdk, @modelcontextprotocol/inspector, @types/node, tsup, typescript
Gates applied: no_behavioural_pass.
23392b073693full audit observations/trust-audit/mcp-server/yukukotani__gemini-google-search.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 23392b073693 | SAFE | B | 89 | first audit |
Questions
What is the Gemini Google Search MCP server?
MCP server for Google Search integration using Gemini's built-in search capabilities
What tools does Gemini Google Search expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Gemini Google Search safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Gemini Google Search need?
It reads GEMINI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Gemini Google Search run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-gemini-google-search at 0.1.1.
How current is this page?
The grade is for one exact copy of the source (23392b073693), read on 2026-10-07. The repository is watched and re-audited when it changes.