Skip to main content
Glama
andreilungeanu

Cursor Delegate

Cursor Delegate

Keep the brains. Delegate the build.

npm version npm downloads node license: MIT tests

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 โ€” or any MCP client โ€” hand implementation to Cursor's CLI agent, then get a clean, structured result back for review.

Demo

๐Ÿง  Frontier quality, kept

Your assistant does what frontier models are actually for: understands the task, writes a precise brief, reviews the finished diff. And Composer 2.5 holds its own โ€” a seriously capable coding model, just guided and checked by a smarter one. The result reads like frontier work, because a frontier model planned it and signed off on it.

Related MCP server: @willpowell8/cursor-cloud-agent-mcp

โšก Done faster

Composer 2.5 is built for speed. It tears through multi-file edits while a frontier model would still be streaming the first file. You delegate, keep working with your assistant, and the diff shows up done.

๐Ÿ”‹ Your limits stop being the bottleneck

Delegated work bills to Composer's own usage pool โ€” separate from Cursor's API-priced main quota, and so generous most users never hit its 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. On API? That's the per-token grind moved off your bill.

You  โ†’  your agent (plans & reviews)
              โ”‚  MCP delegate tool
              โ–ผ
        cursor-agent (Composer 2.5 โ€” implements)
              โ”‚  edits your workspace
              โ–ผ
        Clean result: what changed, which files, the plan

Features

  • ๐Ÿค Native plugins โ€” 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.

  • ๐Ÿ’ฌ No stalled runs โ€” 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 โ€” nothing blocks on a modal waiting for input.

  • ๐Ÿ“ฆ Clean, named results โ€” final answer, changed files, session id, and the plan, returned as one compact JSON payload. Nothing to scrape, nothing to guess.

  • ๐Ÿ“‹ Plan first โ€” plan mode: Cursor drafts a plan, you review it, then the same session implements it.

  • ๐Ÿ” Ask anything โ€” ask mode: read-only Q&A over your codebase, zero file changes.

  • ๐Ÿฉบ Self-diagnosing โ€” a doctor tool that tells you exactly what's missing if setup isn't right.

  • ๐Ÿ”Œ Works everywhere MCP does โ€” VS Code, JetBrains, Windsurf, Visual Studio, and more.

Quick start

You need Node.js 20+ and the Cursor CLI, logged in (cursor-agent login).

Claude Code

/plugin marketplace add andreilungeanu/cursor-delegate-mcp
/plugin install cursor-delegate@cursor-delegate-mcp

Then 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 โ€” Claude writes the brief, Cursor grinds through the files, Claude walks you through the diff.

ChatGPT desktop / Codex

codex plugin marketplace add andreilungeanu/cursor-delegate-mcp
codex plugin add cursor-delegate@cursor-delegate-mcp

GitHub Copilot CLI

copilot plugin install andreilungeanu/cursor-delegate-mcp

More clients

{
  "servers": {
    "cursor-delegate": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "cursor-delegate-mcp"]
    }
  }
}

Or run Chat: Install Plugin From Source with this repository's URL.

Under Settings โ†’ Tools โ†’ AI Assistant โ†’ Model Context Protocol (MCP), add a server with command npx and arguments -y cursor-delegate-mcp.

{
  "mcpServers": {
    "cursor-delegate": {
      "command": "npx",
      "args": ["-y", "cursor-delegate-mcp"]
    }
  }
}

Heads-up: Cascade caps you at 100 tools across all servers.

{
  "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, and any other MCP client

Add the following server to the client's MCP config:

{
  "mcpServers": {
    "cursor-delegate": {
      "command": "npx",
      "args": ["-y", "cursor-delegate-mcp"]
    }
  }
}

License

MIT ยฉ Andrei Lungeanu

Technical reference ยท Security ยท Privacy ยท Terms ยท Changelog

Install Server
A
license - permissive license
A
quality
A
maintenance

Maintenance

โ€“Maintainers
โ€“Response time
1dRelease cycle
20Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage

  • User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.

  • Real-time chat hub for AI agents โ€” Claude Code, Cursor, Cline, Codex over MCP or REST.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/andreilungeanu/cursor-delegate-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server