Ask Llm

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 24+ (the current LTS), on Linux or macOS, and at least one provider CLI installed and authenticated (see Provider setup).

npm install -g @ask-llm/mcp

Claude Code

ask-llm setup --host claude

Setup previews the user-scope registration and the workflows it installs (the Claude Code plugin, or the ask-llm-* skills on other hosts) and asks before applying them. Then try: ask codex to review my last commit. Run ask-llm doctor if anything looks off. See command compatibility for -y, removal, and other hosts.

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

After the global install above, run ask-llm setup --host cursor. It previews the user-scope change to ~/.cursor/mcp.json and asks before writing. Restart Cursor Agent to load the server. For a project-scoped or manual install, see the Cursor host guide.

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

After the global install above, run ask-llm setup --host claude-desktop. It previews the user-scope change to claude_desktop_config.json and asks before writing. Restart Claude Desktop to load the server. See command compatibility for removal, backups, and formats that require manual setup.

OpenCode

After the global install above, run ask-llm setup --host opencode. Setup changes only a plain JSON opencode.json; for JSONC it prints the entry to add manually. OpenCode registration has fixture coverage and awaits verification on an installed host.

Pi

Pi has no built-in MCP client, so it installs the host package instead, which registers native consultation tools. After the global Ask LLM install above, install the package and shared skills:

ask-llm setup --host pi

Then use /skill:ask-llm-review, /skill:ask-llm-multi-review, /skill:ask-llm-compare, /skill:ask-llm-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"] }

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 canonical @ask-llm/mcp package also owns the workflows: slash-command reviews with a validation pipeline, multi-model brainstorming, and opt-in continuous pair review. @ask-llm/plugin remains a dependent bridge for existing installs.

ask-llm setup installs these workflows for you: the plugin in Claude Code, and the same skills, named ask-llm-*, in Codex, Cursor Agent, Grok Build, Gemini CLI, OpenCode and Pi through the pinned skills CLI. In Claude Code the earlier names such as /codex-review keep working. To install only the Claude Code plugin by hand:

/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.

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. For host registration (ask-llm setup, ask-llm remove) and host diagnostics, use the separate ask-llm command; see command compatibility.

# 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	Canonical package: unified MCP server, provider executors, and Claude Code, Cursor Agent, and Pi host assets
@ask-llm/plugin	Dependent bridge for existing plugin and Pi installations
@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

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.