MCP.so
Sign In
A

Ask Gemini Mcp

@Lykhoyda

Repository

About Ask Gemini Mcp

No overview available yet

Basic information

Category

AI & Agents

Transports

stdio

Publisher

Lykhoyda

Submitted by

Anton Lykhoyda

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ask-gemini-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ask-gemini-mcp"
      ],
      "env": {
        "GMCPT_TIMEOUT_MS": "300000",
        "GMCPT_LOG_LEVEL": "warn"
      }
    }
  }
}

Tools

3

Send prompts to Gemini CLI. Supports `@` file syntax, model selection, sandbox mode, and changeMode for structured edits

Retrieve subsequent chunks from cached large responses

Connection test — verify MCP setup without using Gemini tokens

Overview

What is Ask Gemini Mcp?

Ask Gemini Mcp is an MCP server that connects any MCP-compatible AI client (e.g., Claude Code, Claude Desktop, Cursor, Copilot) to the Google Gemini CLI. It enables AI-to-AI collaboration by letting your primary agent send prompts to Gemini, leveraging Gemini’s massive 1M+ token context window for large file and codebase analysis. This server is for developers and AI users who want a second opinion, architecture debates, or deep code review from Gemini while their main AI handles interaction and editing.

How to use Ask Gemini Mcp?

Install via npx -y ask-gemini-mcp and configure it as an MCP tool in your client’s settings. For Claude Code, run claude mcp add gemini-cli -- npx -y ask-gemini-mcp. For other clients (Claude Desktop, Cursor, Codex CLI, OpenCode, any STDIO client), add a gemini-cli entry using the same npx command in the appropriate config file. Prerequisites: Node.js v20.0.0+ and the Google Gemini CLI installed and authenticated. Then invoke tools like ask-gemini by instructing your AI to ask Gemini via the MCP.

Key features of Ask Gemini Mcp

  • Exposes three tools: ask-gemini, fetch-chunk, and ping
  • Supports @ file syntax for direct file analysis
  • Offers sandbox mode for running code in isolated environments
  • Defaults to gemini-3.1-pro-preview with automatic fallback to gemini-3-flash-preview
  • Works with 40+ MCP clients via STDIO transport
  • Requires no API key – uses the authenticated Gemini CLI

Use cases of Ask Gemini Mcp

  • Get a second opinion on coding approach before committing
  • Send architecture proposals to Gemini for critique and alternatives
  • Have Gemini analyze diffs or modified files to catch missed issues
  • Analyze entire codebases (1M+ tokens) that overflow other models
  • Run and test code in sandboxed environments via Gemini

FAQ from Ask Gemini Mcp

What are the prerequisites for using Ask Gemini Mcp?

Node.js v20.0.0 or higher and the Google Gemini CLI must be installed and authenticated on your system.

What tools does Ask Gemini Mcp expose?

It provides ask-gemini (send prompts, supports @ file syntax, model selection, sandbox mode), fetch-chunk (retrieve subsequent chunks from large responses), and ping (test connectivity without using Gemini tokens).

Which models does Ask Gemini Mcp support?

The default model is gemini-3.1-pro-preview for best quality reasoning, with gemini-3-flash-preview as a faster option and automatic fallback when Pro quota is exceeded.

How do I configure Ask Gemini Mcp for my client?

Add a gemini-cli MCP server entry with command npx -y ask-gemini-mcp using STDIO transport. Exact config file locations are provided for Claude Desktop, Cursor, Codex CLI, OpenCode, and generic STDIO clients.

Does Ask Gemini Mcp require authentication?

Yes, authentication is handled by the Google Gemini CLI. You must have the CLI installed and authenticated (e.g., via gcloud auth or gemini auth) before using the server.

Comments

More AI & Agents MCP servers

Mcp Agent

lastmile-ai

Build effective agents using Model Context Protocol and simple workflow patterns

8.4K

MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages

utensils

MCP-NixOS - Model Context Protocol Server for NixOS resources

739

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

507

🛡️ A.I.G（AI-Infra-Guard）

Tencent

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

4.1K

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416