ask-gemini-mcp

stdionone★ 10development

MCP server that enables AI assistants to interact with Google Gemini CLI

Install

How to run this server

[ { "cmd": "npx -y ask-llm-mcp", "imports": [] } ]

server path: ask-gemini-mcp

Tools

What this server exposes

ask-gemini

Send prompts to Gemini CLI with `@` file syntax. 1M+ token context. Live progressive output via `stream-json`

ask-gemini-edit

Get structured OLD/NEW code edit blocks from Gemini

fetch-chunk

Retrieve chunks from cached large responses

ask-codex

Send prompts to Codex CLI. GPT-5.5 with mini fallback. Native session resume via `sessionId`

ask-ollama

Send prompts to local Ollama. Fully private, zero cost. Server-side conversation replay via `sessionId`

ask-llm

Unified orchestrator — pick provider per call. Fan out to all installed providers

multi-llm

Dispatch the same prompt to multiple providers in parallel; returns per-provider responses + usage in one call

get-usage-stats

Per-session token totals, fallback counts, breakdowns by provider/model — all in-memory, no persistence

diagnose

Self-diagnosis: Node version, PATH resolution, provider CLI presence + versions. Read-only

ping

Connection test — verify MCP setup

Configuration

Environment & auth

authnone

Resources