Stop burning your frontier agent's limits on boilerplate.
Delegate edits to Cursor's CLI agent — your agent writes the brief and reviews the diff.
Use your best coding agent where its judgment matters most: understanding the task, shaping the plan, and reviewing the result.
Cursor Delegate is the MCP bridge that lets Claude Code, ChatGPT/Codex, Copilot — or any MCP client — hand implementation to Cursor's CLI agent, then get a clean, structured result back for review.
Your assistant does what frontier models are for: understands the task, writes a precise brief, reviews the finished diff. Composer 2.5 runs the implementation loop under that brief. The bundled skill puts the review step in the loop — the agent that scoped the work reads the changed files back before reporting.
Composer 2.5 is built for throughput on multi-file edits. The whole delegation is one call — brief in, result out — so you review a finished diff instead of babysitting edits landing file by file.
Composer and Grok run on their own usage allowance on every Cursor plan — separate from the API-priced main quota, and generous enough that most people never reach the ceiling. Your Claude or Codex subscription spends tokens only on the brief and the review, so the 5-hour window and weekly limits go a lot further. Paying per token on API? That grind moves onto Cursor capacity you already have.
- 🤝 Native plugins — install into Claude Code, ChatGPT/Codex, or GitHub Copilot CLI and just say "delegate this to Cursor". The shared skill teaches your agent how to delegate well.
- 💬 No stalled runs — if Cursor needs to clarify, it ends the turn and returns the question as a normal result. Your agent reads it and answers by resuming the same session — nothing blocks on a modal waiting for input.
- 📦 Clean, named results — final answer, changed files, session id, and the plan, returned as one compact JSON payload. Nothing to scrape.
- 📋 Plan first —
planmode: Cursor drafts a plan, you review it, then the same session implements it. - 🔍 Ask anything —
askmode: Q&A over your codebase. - 🩺 Self-diagnosing — a
doctortool that tells you exactly what's missing if setup isn't right. - 🔌 Portable — plain stdio MCP, so it runs anywhere: VS Code, JetBrains, Windsurf, Visual Studio, and more.
plan and ask are instructions to the agent, and workspace is its working directory — Security and the delegate reference spell out what the bridge enforces and what it reports back.
You need Node.js 20+ and the Cursor CLI, logged in (cursor-agent login).
/plugin marketplace add andreilungeanu/cursor-delegate-mcp
/plugin install cursor-delegate@cursor-delegate-mcpThen just ask:
Delegate to Cursor: migrate src/api from callbacks to async/await and update the tests, then walk me through what changed.
That's the whole loop — Claude writes the brief, Cursor grinds through the files, Claude walks you through the diff.
codex plugin marketplace add andreilungeanu/cursor-delegate-mcp
codex plugin add cursor-delegate@cursor-delegate-mcpcopilot plugin install andreilungeanu/cursor-delegate-mcp{
"mcpServers": {
"cursor-delegate": {
"command": "npx",
"args": ["-y", "cursor-delegate-mcp"]
}
}
}VS Code — one-click install, or .vscode/mcp.json
Or add it manually:
{
"servers": {
"cursor-delegate": {
"type": "stdio",
"command": "npx",
"args": ["-y", "cursor-delegate-mcp"]
}
}
}Or run Chat: Install Plugin From Source with this repository's URL.
JetBrains AI Assistant — Settings → Tools → AI Assistant → MCP
Under Settings → Tools → AI Assistant → Model Context Protocol (MCP), add a server with command npx and arguments -y cursor-delegate-mcp.
Windsurf — ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"cursor-delegate": {
"command": "npx",
"args": ["-y", "cursor-delegate-mcp"]
}
}
}Heads-up: Cascade caps you at 100 tools across all servers.
Visual Studio 2022 — %USERPROFILE%\.mcp.json
{
"servers": {
"cursor-delegate": {
"type": "stdio",
"command": "npx",
"args": ["-y", "cursor-delegate-mcp"]
}
}
}Requires 17.14+. Note the top-level key is servers, not mcpServers.
Kiro, Kilo Code, Zed — and any other stdio MCP client
Use the portable definition above in the client's own MCP config file.
MIT © Andrei Lungeanu
Technical reference · Security · Privacy · Terms · Changelog



