gemini-mcp CLAUDE.md

gemini-mcp CLAUDE.md is an instructions file for coding agents from mintmcqueen/gemini-mcp. It costs 7,786 tokens per session, scanned A, original, MIT.

A Claude Code instruction document for an MCP server that connects AI clients to Google's Gemini models. It describes support for text, images, documents, audio, video, conversations, file uploads, and image generation.

In plain words
What is it for?
Installing dependencies, understanding the server's components, running it, and developing its Gemini model and file-handling features.
Why use it?
It gives the coding agent project-specific commands, architecture, and implementation context instead of making it infer them from the code.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/mintmcqueen/gemini-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/mintmcqueen/gemini-mcp

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.

agentmods badge for gemini-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mintmcqueen/gemini-mcp/claude-md.svg)](https://agentmods.dev/instructions/mintmcqueen/gemini-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mintmcqueen/gemini-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mintmcqueen/gemini-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,786 This file is loaded in full into every session.
When invoked 7,786 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.07786 $0.07786
Opus 5 $0.03893 $0.03893
Sonnet 5 $0.01557 $0.01557
Haiku 4.5 $0.00779 $0.00779

Measured 4d ago against content hash 2edb69cf5e8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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 · 850 lines

How it starts

The opening of the file, as written. The whole thing — 850 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini MCP Server - Technical Documentation

Project Overview

Name: gemini-mcp Version: 0.5.0 Type: Model Context Protocol (MCP) Server Purpose: Provides MCP-compliant interface to Google's Gemini AI models including Gemini 3.1 Pro (default), Gemini 2.5 Pro, Gemini 2.5 Flash, and image generation models (Gemini 3 Pro Image, Gemini 2.5 Flash Image) with advanced file handling, conversation management, and multimodal capabilities.

Key Value Proposition:

  • Gemini 3 Support: Default to Google's most intelligent model with state-of-the-art reasoning and multimodal understanding
  • Image Generation: Text-to-image and image editing with Gemini 3 Pro Image (default) or Gemini 2.5 Flash Image
  • Enables Claude Desktop and other MCP clients to leverage Gemini's thinking models and extended context windows
  • Handles complex file upload workflows including batch processing, retry logic, and state monitoring
  • Manages conversation sessions with full history tracking
  • Supports multimodal interactions (text, images, documents, audio, video)
  • Simple npx Installation: Works with npx @mintmcqueen/gemini-mcp@latest - no global install required

Architecture

High-Level Component Flow

MCP Client (Claude Desktop)
    ↓
StdioServerTransport (stdin/stdout communication)
    ↓
MCP Server (Server class from @modelcontextprotocol/sdk)
    ↓
GeminiMCPServer (Custom implementation)
    ├── Resource Handlers (gemini://models/available, gemini://conversations/active, gemini://files/uploaded)
    ├── Tool Handlers (chat, generate_images, upload_file, batch_upload_files, list_files, get_file, delete_file, cleanup_all_files)
    └── State Management (conversations Map, uploadedFiles Map, fileObjects Map)
        ↓
GoogleGenAI SDK (@google/genai)
    ↓
Gemini API (Google's REST API)

Core Components

1. GeminiMCPServer Class (src/index.ts:59-1138)

Main server orchestration class that manages:

  • MCP protocol compliance via @modelcontextprotocol/sdk
  • Request routing to appropriate handlers
  • Internal state (conversations, uploaded files, file objects)
  • Error handling and graceful shutdown

Read the full file on GitHub · 850 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.

  1. 4d ago First seen · 850 lines · 7,786 tokens per session scan A 2edb69cf5e8f

Subscribe to this mod's changes

gemini-mcp CLAUDE.md is an instructions file published in the GitHub repository mintmcqueen/gemini-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 7,786 tokens to every session, about $0.0389 per session on Opus 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 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens