An MCP server that connects MCP clients to Google Gemini CLI for AI-to-AI collaboration. It lets clients send prompts, analyze files or codebases, retrieve large responses in chunks, and test the connection.
From the registry: Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions
Please install the `ask-gemini` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js** — Node.js v20.0.0 or higher (LTS) is required to run the MCP server via npx. (https://nodejs.org/)
- **Install and authenticate Google Gemini CLI** — The Google Gemini CLI must be installed and authenticated before using this MCP server, since the server connects AI clients to Gemini CLI. (https://github.com/google-gemini/gemini-cli)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","ask-gemini-mcp"]
Note: README provides a generic STDIO configuration for any MCP client. No MCP-specific environment variables are documented for this server.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.