Ask LLM

Give your AI coding assistant a second opinion — from a different model.

Claude Code, Codex CLI, Cursor, Claude Desktop, or any of 40+ MCP clients can call Codex, Claude, Grok, Antigravity, Ollama, or Gemini to review a diff, debate a plan, or catch the bug the first model missed. Standard MCP; no prompt hacks.

Quick Start · Choose a reviewer · Claude Code plugin · Docs · Packages

You:    ask codex to review src/auth.ts for security issues
Codex:  ⚠ verifyToken() compares tokens with === — not timing-safe (line 42)
        ⚠ the session cookie is missing a SameSite attribute
Claude: Good catches — applying both fixes to src/auth.ts.

One prompt. A second model reviews independently; your assistant applies the fix. No copy-pasting between tools.

Why a second opinion?

Your primary AI is confident, but confidence isn't correctness. A second model with no stake in the first answer catches what it glossed over.

Quick Start

Prerequisites: Node.js 20+ and at least one provider CLI installed and authenticated (see Provider setup).

Claude Code

# One install, every provider — auto-detects what you have
claude mcp add --scope user ask-llm -- npx -y @ask-llm/mcp

Then try: ask codex to review my last commit. Run npx @ask-llm/mcp doctor if anything looks off.

claude mcp add --scope user codex -- npx -y @ask-llm/codex-mcp
claude mcp add --scope user grok -e XAI_API_KEY="$XAI_API_KEY" -- npx -y @ask-llm/grok-mcp
claude mcp add --scope user antigravity -- npx -y @ask-llm/antigravity-mcp
claude mcp add --scope user ollama -- npx -y @ask-llm/ollama-mcp
claude mcp add --scope user gemini -- npx -y @ask-llm/gemini-mcp

Cursor

Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (user):

{
  "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"]

Want Codex to consult Claude specifically? codex mcp add claude -- npx -y @ask-llm/claude-mcp

Claude Desktop

Add to claude_desktop_config.json:

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

Pi

Pi has no built-in MCP client, so it installs the host package instead, which registers native ask-* tools plus the shared skills:

pi install npm:@ask-llm/plugin

Then use /skill:codex-review, /skill:multi-review, /skill:compare, /skill:brainstorm, or just describe what you want. See the Pi host guide for trust, data-transfer, and compatibility details.

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

Swap @ask-llm/mcp for @ask-llm/codex-mcp, @ask-llm/claude-mcp, @ask-llm/grok-mcp, @ask-llm/antigravity-mcp, @ask-llm/ollama-mcp, or @ask-llm/gemini-mcp to install a single provider.

Choose your reviewer

The unified @ask-llm/mcp server is the recommended install: one registration, every provider you have, and parallel fan-out via multi-llm. Each provider is also available standalone.

Gemini CLI is enterprise-only since 2026-06-18. Google restricted Gemini CLI to Gemini Code Assist Standard/Enterprise seats; free, Google AI Pro, and Ultra accounts lost access. @ask-llm/gemini-mcp still installs, but non-enterprise accounts get actionable guidance instead of output. On a subscription plan, use Antigravity (Google's sanctioned successor, covered by AI Pro/Ultra), Codex, Claude, or Ollama. Announcement

Fallbacks fire only under each provider's documented conditions (quota for Gemini/Codex, overload for Claude, rate limit for Antigravity). Grok and Ollama never substitute a model: Grok sends the exact harness catalog ID unchanged, and Ollama returns a clear ollama pull error if the requested model isn't local. Full details in Model Selection.

The Ask LLM plugin (Claude Code, Cursor Agent, Pi)

MCP gives your assistant the tools. The plugin, @ask-llm/plugin, adds the workflows: slash-command reviews with a validation pipeline, multi-model brainstorming, and opt-in continuous pair review.

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

Review agents follow 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.

@ask-llm/plugin is one package, one version, one release lifecycle, and one canonical skill corpus. Claude Code loads its marketplace agents and hooks; Cursor Agent loads the adapted /codex-pair and /grok-pair skills through Agent Skills plus mcp.json (agent --plugin-dir ./packages/claude-plugin; see the Cursor Agent host guide); Pi loads explicit native tools, portable skill adapters, and a thin lifecycle extension.

Pi specifics: codex-pair requires the repository marker, Pi project trust, and interactive user-owned consent via /codex-pair; a committed marker alone never authorizes source transfer or cost. Pi surfaces findings non-blockingly and does not claim Claude's blocking Stop gate or one-shot print parity. fable-review is Claude Code-only. Provider CLI authentication is separate from Pi's host-model login. Update or remove with pi update npm:@ask-llm/plugin / pi remove npm:@ask-llm/plugin.

See the plugin docs for hooks, agents, and configuration.

MCP tools

Session-capable ask-* tools accept an optional sessionId and return a structured AskResponse (provider, response, model, sessionId, usage) via MCP outputSchema alongside the human-readable text. Codex requires sessionId: "" on the first call for a resumable thread. The orchestrator also exposes usage://current-session as an MCP Resource for live JSON snapshots.

Things to say

ask codex to review the changes in src/auth.ts for security issues
ask claude for an independent opinion on this architecture        (from Codex or another non-Claude client)
ask antigravity to debate the plan in docs/design.md
ask ollama to explain src/config.ts                                 (runs locally, nothing leaves your machine)
ask gemini to summarize @. the current directory                    (1M+ context; @ syntax is Gemini-only)
use multi-llm to compare what codex and grok think about this approach

More patterns in How to Ask and Multi-Turn Sessions.

CLI

The @ask-llm/mcp binary (ask-llm-mcp) starts the MCP server when run with no arguments. With arguments it's a CLI; ask-llm-mcp --help is the canonical reference.

# Diagnose your setup: Node version, PATH, provider CLI versions, env vars
npx @ask-llm/mcp doctor                       # human-readable
npx @ask-llm/mcp doctor --json                # full JSON, exit 1 on error
npx @ask-llm/mcp doctor --format toon         # bounded, versioned agent-facing TOON pilot
npx @ask-llm/mcp doctor --format toon --full  # full TOON escape hatch

# Interactive multi-provider REPL: switch providers, persist sessions, watch usage live
npx @ask-llm/mcp repl

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

Provider setup

Install and authenticate whichever providers you want to consult. The unified server detects what's present.

Packages

Package	What it is	Version	Downloads
@ask-llm/mcp	Unified MCP server (recommended): all providers, multi-llm, ask-cursor-agent, doctor, REPL
@ask-llm/plugin	Claude Code + Cursor Agent + Pi host package (skills, agents, hooks)
@ask-llm/codex-mcp	Codex-only MCP server
@ask-llm/claude-mcp	Claude-only MCP server
@ask-llm/grok-mcp	Grok-only MCP server
@ask-llm/antigravity-mcp	Antigravity-only MCP server
@ask-llm/ollama-mcp	Ollama-only MCP server
@ask-llm/gemini-mcp	Gemini-only MCP server

All public MCP packages now live in the @ask-llm npm organization. The old names are deprecated, but executable names are unchanged: update the package argument in your MCP config and commands such as ask-codex-mcp and ask-llm-mcp doctor keep working after a global install.

The installation guide has the complete package-to-executable mapping.

Documentation

• Docs site: lykhoyda.github.io/ask-llm — Getting Started, How It Works, Troubleshooting
• For AI agents: llms.txt · llms-full.txt

Contributing

Contributions are welcome. Start with the open issues and CONTRIBUTING.md.

License

MIT. See LICENSE.

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