Ask LLM

Package	Type	Version	Downloads
ask-gemini-mcp	MCP Server
ask-codex-mcp	MCP Server
ask-ollama-mcp	MCP Server
ask-llm-mcp	MCP Server
@ask-llm/plugin	Claude Code Plugin		/plugin install

MCP servers + Claude Code plugin for AI-to-AI collaboration

MCP servers that bridge your AI client with multiple LLM providers for AI-to-AI collaboration. Works with Claude Code, Claude Desktop, Cursor, Warp, Copilot, and 40+ other MCP clients. Leverage Gemini's 1M+ token context, Codex's GPT-5.5, or local Ollama models — all via standard MCP.

Why?

• Get a second opinion — Ask another AI to review your coding approach before committing
• Debate plans — Send architecture proposals for critique and alternative suggestions
• Review changes — Have multiple AIs analyze diffs to catch issues your primary AI might miss
• Massive context — Gemini reads entire codebases (1M+ tokens) that would overflow other models
• Local & private — Use Ollama for reviews where no data leaves your machine

Quick Start

Claude Code

# All-in-one — auto-detects installed providers
claude mcp add --scope user ask-llm -- npx -y ask-llm-mcp

claude mcp add --scope user gemini -- npx -y ask-gemini-mcp
claude mcp add --scope user codex -- npx -y ask-codex-mcp
claude mcp add --scope user ollama -- npx -y ask-ollama-mcp

Claude Desktop

Add to claude_desktop_config.json:

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

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

Cursor (.cursor/mcp.json):

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

Codex CLI (~/.codex/config.toml):

[mcp_servers.ask-llm]
command = "npx"
args = ["-y", "ask-llm-mcp"]

Any MCP Client (STDIO transport):

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

Replace ask-llm-mcp with ask-gemini-mcp, ask-codex-mcp, or ask-ollama-mcp for a single provider.

Claude Code Plugin

The Ask LLM plugin adds multi-provider code review, brainstorming, and automated hooks directly into Claude Code:

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

What You Get

The review agents use a 4-phase pipeline inspired by Anthropic's code-review plugin: context gathering, prompt construction with explicit false-positive exclusions, synthesis, and source-level validation of each finding.

See the plugin docs for details.

Prerequisites

• Node.js v20.0.0 or higher (LTS)
• At least one provider:
  • Gemini CLI — npm install -g @google/gemini-cli && gemini login
  • Codex CLI — installed and authenticated
  • Ollama — running locally with a model pulled (ollama pull qwen2.5-coder:7b)

MCP Tools

All ask-* tools accept an optional sessionId parameter for multi-turn conversations and now return a structured AskResponse (provider, response, model, sessionId, usage) via MCP outputSchema alongside the human-readable text. The orchestrator (ask-llm-mcp) also exposes usage://current-session as an MCP Resource for live JSON snapshots.

Usage Examples

ask gemini to review the changes in @src/auth.ts for security issues
ask codex to suggest a better algorithm for @src/sort.ts
ask ollama to explain @src/config.ts (runs locally, no data sent anywhere)
use gemini to summarize @. the current directory
use multi-llm to compare what gemini and codex think about this approach

CLI Subcommands

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

# Interactive multi-provider REPL — switch providers, persist sessions, see usage live
npx ask-llm-mcp repl

# Diagnose your setup — Node version, PATH, provider CLI versions, env vars
npx ask-llm-mcp doctor          # human-readable
npx ask-llm-mcp doctor --json   # machine-readable, exit 1 on error

The REPL ships sessions per provider (/provider gemini, /provider codex, /new, /sessions, /usage) and inherits all the executor behavior (quota fallback, stream-json output for Gemini, native session resume).

Models

All providers automatically fall back to a lighter model on errors.

Documentation

• Docs site: lykhoyda.github.io/ask-llm
• AI-readable: llms.txt | llms-full.txt

Contributing

Contributions are welcome! See open issues for things to work on.

License

MIT License. See LICENSE for details.

Disclaimer: This is an unofficial, third-party tool and is not affiliated with, endorsed, or sponsored by Google or OpenAI.