What is mcp-gemini-google-search CLAUDE.md?

Project instructions for an MCP server that lets an AI assistant use Google Search through Google's Gemini service. MCP is a standard way for an AI assistant to call external tools.

Use it when developing, testing, debugging, or publishing this TypeScript Google Search server, including its search tool, Gemini model setting, environment checks, and citation metadata.

It gives contributors the commands, file map, configuration details, and architecture needed to build and inspect the server consistently.

How yukukotani/mcp-gemini-google-search configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to yukukotani/mcp-gemini-google-search. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/yukukotani/mcp-gemini-google-search/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/yukukotani/mcp-gemini-google-search

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/yukukotani/mcp-gemini-google-search/claude-md/github.svg)](https://agentmods.dev/instructions/yukukotani/mcp-gemini-google-search/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/yukukotani/mcp-gemini-google-search/claude-md"><img src="https://agentmods.dev/badge/instructions/yukukotani/mcp-gemini-google-search/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/yukukotani/mcp-gemini-google-search/claude-md"><img src="https://agentmods.dev/badge/instructions/yukukotani/mcp-gemini-google-search/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 588 This file is loaded in full into every session.

When invoked 588 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00588	$0.00588
Opus 5.5	$0.00235	$0.00235
Sonnet 5.5	$0.00118	$0.00118
Haiku 4.5	$0.00059	$0.00059

Measured 2mo ago against content hash 0776a2770938, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-gemini-google-search CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Development Commands

npm run build - Build TypeScript (generates both ESM and CJS)
npm run dev - Watch for file changes and rebuild
npm run start - Run the built server
npm run inspect - Debug with MCP Inspector
npm run prepublishOnly - Automatic build before release

Architecture

This project is a Model Context Protocol (MCP) server that provides Google Search functionality using Gemini's built-in Google Search feature.

Key Components

src/index.ts: Main entry point for the MCP server
- Uses stdio transport
- Registers and handles the google_search tool
- Environment variable validation is handled in createGoogleSearchAI
src/tools/google-search.ts: Google Search implementation
- Uses @google/genai SDK to access Gemini
- Model can be configured via GEMINI_MODEL environment variable
- Enables the googleSearch tool via ai.models.generateContent
- Extracts grounding metadata from responses to add citation information
- Reference implementation: https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/tools/web-search.ts

Tech Stack

TypeScript + Node.js 18+
@google/genai (Google's unified GenAI SDK)
@modelcontextprotocol/sdk
tsup for dual ESM/CJS build

Type Error Resolution Notes

The @google/genai API uses ai.models.generateContent
Tools parameter format: config: { tools: [{ googleSearch: {} }] }
Response access structure: response.candidates[0].content.parts
Grounding metadata is located at response.candidates[0].groundingMetadata

Environment Variables

For Google AI Studio (default):

GEMINI_API_KEY: Google AI Studio API key (required)
GEMINI_MODEL: Model to use (optional, default: gemini-2.5-flash)

For Vertex AI:

GEMINI_PROVIDER: Set to "vertex"
VERTEX_PROJECT_ID: GCP project ID (required)
VERTEX_LOCATION: Region (optional, default: us-central1)
GEMINI_MODEL: Model to use (optional, default: gemini-2.5-flash)

Read the full file on GitHub · 61 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 61 lines · 588 tokens per session scan A 0776a2770938

Subscribe to this mod's changes

mcp-gemini-google-search CLAUDE.md is an instructions file published in the GitHub repository yukukotani/mcp-gemini-google-search (83 stars, last pushed 1y ago), licensed Apache-2.0. It adds 588 tokens to every session, about $0.0024 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

mcp-server

mcp-gemini-google-search CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-gemini-google-search CLAUDE.mdyukukotani/mcp-gemini-google-search	Instructions file	83	1y ago	Apache-2.0	A	588	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-gemini-google-search: Instructions file for Claude Code