Unified (ask-llm-mcp)

All providers in one MCP server. Auto-detects which CLIs are installed and registers only the available tools. One install, all providers.

Installation

Run in your terminal:

# Project scope (current project only)
claude mcp add ask-llm -- npx -y ask-llm-mcp

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

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

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

Or install globally:

npm install -g ask-llm-mcp

Prerequisites

1. Node.js v20.0.0 or higher
2. At least one provider installed and authenticated:
   • Gemini CLI for ask-gemini tools
   • Codex CLI for ask-codex tools
   • Ollama running locally for ask-ollama tools

How It Works

On startup, the unified server:

1. Checks for CLI availability via which (Gemini, Codex)
2. Checks for HTTP availability via health endpoints (Ollama)
3. Dynamically imports and registers tools from available providers
4. Exposes only the tools for providers that are actually installed

Tools

All tools from installed providers are registered. If you have all three:

Tool	Purpose
ask-llm	Single unified tool — picks the provider via provider parameter (gemini, codex, ollama). Optional sessionId for multi-turn continuation
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 + breakdowns by provider/model — in-memory, no persistence
diagnose	Self-diagnosis: Node version, PATH, provider CLI presence + versions. Read-only
ping	Connection test

The orchestrator uses a single ask-llm tool (not one per provider) for token efficiency — see ADR-029. All ask-* tools return both human-readable text and a structured AskResponse (provider, response, model, sessionId, usage) via MCP outputSchema.

It also exposes usage://current-session as an MCP Resource for live JSON snapshots of token spend.

CLI Subcommands

The ask-llm-mcp binary supports two CLI modes alongside the default MCP server:

npx ask-llm-mcp repl     # interactive multi-provider REPL with sessions, usage tracking, slash commands
npx ask-llm-mcp doctor   # diagnose Node version, PATH, provider CLIs, env vars (--json for machine output)

Key Features

• Single server for all providers
• Auto-detection of installed CLIs
• Single unified ask-llm tool for token efficiency
• Multi-provider parallel dispatch via multi-llm (Promise.all internally; per-provider failure isolation)
• Session continuity across all 3 providers — Gemini (--resume), Codex (exec resume), Ollama (server-side replay)
• Graceful degradation if a provider is unavailable

npm

• Package: ask-llm-mcp
• Binary: ask-llm-mcp