Let your AI assistant consult Codex, Antigravity, Ollama, or Gemini for an independent code review, a plan debate, or a fresh pair of eyes on a diff. Standard MCP — works in Claude Code, Cursor, Claude Desktop, and 40+ clients.
youask codex to review src/auth.ts for security issues
codex⚠ verifyToken() compares tokens with === — not timing-safe (line 42)
codex⚠ the session cookie is missing a SameSite attribute
claudeGood catches — applying both fixes to src/auth.ts.
One prompt. A second model reviews independently; your assistant applies the fix.
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 the opt-in continuous codex-pair review hook):
/plugin marketplace add Lykhoyda/ask-llm
/plugin install ask-llm@ask-llm-pluginsGet started in minutes. Pick your client, add the MCP server, and you're live. Requires Node.js v20+ and the relevant CLI authenticated.
Ask your AI assistant: Use ask-llm ping to test the connection. Got Pong! back? You're ready. See How to Ask for usage examples.
Works with 40+ MCP-compatible clients. No prompt hacks. Your primary LLM transparently delegates research, reviews, or brainstorming to other providers.
Continue conversations across multiple calls. Review code, then follow up for fixes. See Multi-Turn Sessions for details.