MCP.so
Sign In
A

Ask Gemini Mcp

@Lykhoyda

Repository

About Ask Gemini Mcp

No overview available yet

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

5

Send a prompt to Gemini CLI (defaults to gemini-3.1-pro-preview with automatic Flash fallback on quota errors). Use for code review, second opinions, analysis, and AI-to-AI collaboration. Do not override the model parameter unless the user explicitly asks. Returns both human-readable text and a structured response (provider, model, sessionId, usage) via outputSchema.

Send a code edit request to Gemini CLI and get structured OLD/NEW edit blocks back. Gemini analyzes the files and returns precise, applicable code changes. Use this when you want Gemini to suggest specific code modifications rather than just analysis.

Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response.

Test connectivity with the MCP server

Get the current MCP server's session usage stats: total LLM calls, token totals (input/output/thinking/cached), wall time, and breakdowns per provider and per model. No data leaves your machine — counts are tracked in-memory for the lifetime of the server process. Returns both human-readable markdown and a structured JSON snapshot via outputSchema.

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.

Frequently asked questions

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

Basic information

Category

AI & Agents

Transports

stdio

Author

Lykhoyda

Submitted by

Anton Lykhoyda

More AI & Agents MCP servers

🔎 GPT Researcher

assafelovic

An autonomous agent that conducts deep research on any data using any LLM providers

28.1K

GetIntel

tarang8811

Public docs + tool manifest for the GetIntel MCP connector (app.getintel.ai)

Agentery

ntlgnc

Free MCP for live and historical pricing for 13,000+ agents and MCPs. Never knowingly pay too much... or charge too little. Know the going rate. https://agentery.com.

BlazingCDN MCP - Content Delivery for Video, Software & Static Files

BlazingCDN

Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN

1

Agentic Atlas

Avery Jones

Consult field-tested agent-system design patterns through 8 hosted, read-only tools for orientation, deep reading, relationships, provenance, glossary terms, and publication decisions.