ask-gemini

v0.3.6Coding Agentsstable

An MCP server for AI-to-AI collaboration via the Gemini CLI. Available on npm: ask-gemini-mcp. Works with Claude Code, Claude Desktop, Cursor, Warp, Copilot, and 40+ other MCP clients. Leverage Gemini's massive 1M+ token context window for large file

aiclaudeclaude-aiclaude-codeclaude-mcp
Share:
10
Stars
0
Downloads
0
Weekly
0/5

What is ask-gemini?

ask-gemini is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for ai-to-ai collaboration via the gemini cli. available on npm: ask-gemini-mcp. works with claude code, claude desktop, cursor, warp, copilot, and 40+ other mcp clients. leverage gemini's ...

An MCP server for AI-to-AI collaboration via the Gemini CLI. Available on npm: ask-gemini-mcp. Works with Claude Code, Claude Desktop, Cursor, Warp, Copilot, and 40+ other MCP clients. Leverage Gemini's massive 1M+ token context window for large file

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An MCP server for AI-to-AI collaboration via the Gemini CLI.

Use Cases

AI-to-AI collaboration with Gemini
Leverage massive 1M+ token context window
Lykhoyda

Maintainer

LicenseMIT License
Languagetypescript
Versionv0.3.6
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y ask-codex-mcp

Manual Installation

npx -y ask-codex-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use ask-gemini

ask-gemini is an MCP server enabling AI-to-AI collaboration by letting Claude invoke Google Gemini directly through natural-language tool calls. It leverages Gemini's 1M+ token context window for analyzing large files, cross-reviewing code, and getting a second AI opinion — all without leaving your Claude Code or Claude Desktop session. Also available as part of the unified ask-llm-mcp package supporting Codex, Ollama, and Antigravity.

Prerequisites

  • Node.js 18+ installed with npm
  • Google Gemini CLI installed and authenticated (npm install -g @google/gemini-cli and gemini auth login)
  • Claude Code CLI or Claude Desktop as the MCP client
  • An active Google account with Gemini API access
1

Install and authenticate the Gemini CLI

The ask-gemini MCP server delegates to the Gemini CLI, so it must be installed and authenticated first.

npm install -g @google/gemini-cli
gemini auth login
2

Add the ask-gemini server to Claude Code

Register the server using the Claude Code CLI. This installs the ask-gemini-mcp package on first run via npx.

claude mcp add --scope user gemini -- npx -y ask-gemini-mcp
3

Configure Claude Desktop (alternative)

For Claude Desktop, add the server entry to claude_desktop_config.json. No API keys are needed in the config — authentication flows through the already-authenticated Gemini CLI.

{
  "mcpServers": {
    "ask-gemini": {
      "command": "npx",
      "args": ["-y", "ask-gemini-mcp"]
    }
  }
}
4

Install the unified multi-LLM package (optional)

To also get Codex, Ollama, and Antigravity support alongside Gemini in one package, use ask-llm-mcp instead.

claude mcp add --scope user ask-llm -- npx -y ask-llm-mcp
5

Verify by asking Gemini a question

Restart Claude and ask it to consult Gemini on something. Claude will invoke the ask-gemini tool and relay Gemini's response.

ask-gemini Examples

Client configuration

Claude Desktop configuration for ask-gemini-mcp. Authentication is handled by the Gemini CLI, so no API keys are needed in the config.

{
  "mcpServers": {
    "ask-gemini": {
      "command": "npx",
      "args": ["-y", "ask-gemini-mcp"]
    }
  }
}

Prompts to try

Example prompts for AI-to-AI collaboration, large file analysis, and cross-model code review.

- "Ask Gemini to review the changes in src/auth.ts for security issues"
- "Ask Gemini to summarize this 500-page PDF — it has a 1M token context window"
- "Get Gemini's opinion on this system architecture design in docs/design.md"
- "Ask Gemini and compare its answer to yours: what is the best approach for rate limiting a REST API?"
- "Use multi-llm to ask both Gemini and Codex to review my database migration script"

Troubleshooting ask-gemini

Gemini CLI not authenticated or command not found

Run: npm install -g @google/gemini-cli && gemini auth login. After authentication, test with: gemini -p 'Hello' in your terminal to confirm the CLI works before trying the MCP server.

npx ask-gemini-mcp fails with package not found

Verify the npm registry is accessible: npm ping. Clear the npx cache with: npx clear-npx-cache. The correct package name is ask-gemini-mcp (not ask-codex-mcp which is the Codex variant).

Gemini returns truncated responses for large files

Use the fetch-chunk tool available in the ask-llm-mcp unified package to split large content into chunks before sending. The 1M token window is on Gemini's side, but the MCP transport has its own message size limits.

Frequently Asked Questions about ask-gemini

What is ask-gemini?

ask-gemini is a Model Context Protocol (MCP) server that mcp server for ai-to-ai collaboration via the gemini cli. available on npm: ask-gemini-mcp. works with claude code, claude desktop, cursor, warp, copilot, and 40+ other mcp clients. leverage gemini's massive 1m+ token context window for large file It connects AI assistants to external tools and data sources through a standardized interface.

How do I install ask-gemini?

Install via npm with the command: npx -y ask-codex-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with ask-gemini?

ask-gemini works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is ask-gemini free to use?

Yes, ask-gemini is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "ask-gemini": { "command": "npx", "args": ["-y", "ask-codex-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use ask-gemini?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides