Skip to content

Gemini

Bridge Claude with Google's Gemini via the official Gemini CLI. Leverages Gemini's massive 1M+ token context window for large file and codebase analysis while Claude handles interaction and code editing.

Installation

Run in your terminal:

bash
# Project scope (current project only)
claude mcp add gemini-cli -- npx -y ask-gemini-mcp

# User scope (all projects)
claude mcp add --scope user gemini-cli -- npx -y ask-gemini-mcp

Or install as a plugin (adds slash commands like /multi-review, /brainstorm, /compare, plus reviewer subagents and a pre-commit hook):

bash
/plugin marketplace add Lykhoyda/ask-llm
/plugin install ask-llm@ask-llm-plugins

Or install globally:

bash
npm install -g ask-gemini-mcp

Prerequisites

  1. Node.js v20.0.0 or higher
  2. Gemini CLI installed and authenticated:
bash
npm install -g @google/gemini-cli
gemini login

Tools

ToolPurpose
ask-geminiSend prompts to Gemini CLI with @ file syntax. Optional sessionId for multi-turn; live progressive output via --output-format stream-json (ADR-057)
ask-gemini-editStructured code edits via Gemini changeMode. Returns OLD/NEW edit blocks. Supports includeDirs for monorepo context
fetch-chunkRetrieve subsequent chunks from cached large responses
get-usage-statsPer-session token totals + breakdowns by provider/model. In-memory (ADR-054)
pingFast connection test to verify MCP setup

ask-gemini returns both human-readable text and a structured AskResponse (provider, response, model, sessionId, usage) via MCP outputSchema — programmatic clients can extract the sessionId and usage fields directly without parsing the response footer (ADR-065).

Models

  • Default: gemini-3.1-pro-preview (latest, highest capability)
  • Fallback: gemini-3-flash-preview (automatic on quota errors per ADR-044)

Key Features

  • 1M+ token context for analyzing entire codebases
  • Multi-turn sessions via sessionId — native --resume <id> (zero replay cost)
  • Include directories for monorepo context (includeDirs parameter on ask-gemini-edit)
  • Live progressive output — assistant message deltas stream to MCP progress notifications, no frozen waits on long calls
  • Structured AskResponse via outputSchema for programmatic clients
  • Automatic quota fallback from Pro to Flash on RESOURCE_EXHAUSTED

npm

Released under the MIT License.