Cursor Delegate

Cursor Delegate

Enables MCP clients like Claude Code and Codex to delegate coding tasks to Cursor's CLI agent, which implements changes in the workspace and returns clean, structured results for review.

Category
Visit Server

README

Cursor Delegate

Keep the brains. Delegate the build.

npm version npm downloads node license: MIT tests

<img src="assets/logo-light.png" alt="Cursor Delegate logo" width="150" align="left" hspace="15">

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.

<br clear="left">

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.

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

<details> <summary><strong>VS Code</strong> โ€” <code>.vscode/mcp.json</code></summary>

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

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

</details>

<details> <summary><strong>JetBrains AI Assistant</strong> โ€” Settings โ†’ Tools โ†’ AI Assistant โ†’ MCP</summary>

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

</details>

<details> <summary><strong>Windsurf</strong> โ€” <code>~/.codeium/windsurf/mcp_config.json</code></summary>

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

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

</details>

<details> <summary><strong>Visual Studio 2022</strong> โ€” <code>%USERPROFILE%.mcp.json</code></summary>

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

Requires 17.14+. Note the top-level key is servers, not mcpServers.

</details>

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

<sub>Technical reference ยท Security ยท Privacy ยท Terms ยท Changelog</sub>

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured