What is Gemini-mcp CLAUDE.md?

A guide for an MCP server that gives Claude Code and other MCP clients five tools for working with Gemini models. MCP is a standard way for an AI assistant to call external tools; the server supports questions, content and code analysis, brainstorming, and search.

Use it when configuring, building, running, or changing the Gemini MCP server and its five tools.

It explains the server's architecture, authentication options, models, and build process so developers can maintain or run it correctly.

How LKbaba/Gemini-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to LKbaba/Gemini-mcp. 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/LKbaba/Gemini-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/LKbaba/Gemini-mcp

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/lkbaba/gemini-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/lkbaba/gemini-mcp/claude-md)

Your own site

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

Per session 841 This file is loaded in full into every session.

When invoked 841 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	$0.00841	$0.00841
Opus 5.5	$0.00336	$0.00336
Sonnet 5.5	$0.00168	$0.00168
Haiku 4.5	$0.00084	$0.00084

Measured 2mo ago against content hash 8312182cfc8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Gemini-mcp 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Overview

Name: mcp-server-gemini (npm: @lkbaba/mcp-server-gemini)
Version: 2.0.0
Purpose: MCP server providing 5 Gemini AI tools for Claude Code and other MCP clients
Author: LKbaba (based on aliargun/mcp-server-gemini v4.2.2)

Architecture

Protocol layer: @modelcontextprotocol/sdk v1.29+ (v2.0 migration; v1.x used hand-written JSON-RPC)
Auth: Dual mode — AI Studio API Key (GEMINI_API_KEY) or Vertex AI ADC (service account / gcloud)
Auth detection: gemini-factory.ts:detectAuthConfig() with 3-mode priority: explicit Vertex AI → raw JSON paste → API Key
Default Vertex AI location: global (required for Gemini 3.x preview models)
5 Tools: multimodal_query, analyze_content, analyze_codebase, brainstorm, search
Models: gemini-3.1-pro-preview (default), gemini-3.5-flash (search default, GA)
Build: TypeScript → dist/, run with node dist/server.js

Key Implementation Details

server.ts uses Server + StdioServerTransport + setRequestHandler(ListToolsRequestSchema | CallToolRequestSchema); notifications are handled silently by the SDK (fixes the v1 notifications/initialized spec violation that caused Connection closed in strict MCP clients)
Gemini clients are lazy-initialized on first tools/call — auth errors surface at call time, not at startup
Tool errors are mapped to SDK McpError with ErrorCode.InvalidParams / InternalError / MethodNotFound
Windows MCP clients corrupt / → \ in env vars; fixWindowsSlashCorruption() in gemini-factory.ts handles this
Service account credentials written to temp file via setupCredentialsTempFile() to avoid PEM encoding issues
GeminiClient wraps GoogleGenAI for 4 tools; search.ts receives raw GoogleGenAI instance directly
Tool input schemas in tools/definitions.ts are still hand-written JSON Schema (SDK accepts both; Zod migration deferred)

Development Environment

OS: Windows 10.0.19045
Shell: Git Bash
Path format: Windows (use forward slashes in Git Bash)
File system: Case-insensitive
Line endings: CRLF (configure Git autocrlf)

Read the full file on GitHub · 59 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 · 59 lines · 841 tokens per session scan A 8312182cfc8e

Subscribe to this mod's changes

Gemini-mcp CLAUDE.md is an instructions file published in the GitHub repository LKbaba/Gemini-mcp (141 stars, last pushed 4mo ago), licensed MIT. It adds 841 tokens to every session, about $0.0034 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.

Gemini-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Gemini-mcp CLAUDE.mdLKbaba/Gemini-mcp	Instructions file	141	4mo ago	MIT	A	841	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	today	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

Gemini-mcp: Instructions file for Claude Code