Cursor Delegate

io.github.andreilungeanu由 GitHub 帳號 andreilungeanu 發布v2.8.0更新於 Nov 8, 2026

Bridge AI coding hosts to cursor-agent over the Agent Client Protocol.

已驗證STDIO僅桌面開發者工具AI 與機器學習

概覽

AI 產生的概覽

把 MCP 用戶端接到 Cursor 的命令列代理,讓助理把程式實作外包出去並取回結構化結果供審閱。

可以做什麼
  • 把寫好的任務說明交給 Cursor 命令列代理,一次回傳最終答覆、變更檔案、工作階段 ID 與計畫組成的 JSON
  • 先產出計畫,審閱後在同一工作階段中實作
  • 針對程式碼庫提問
  • 恢復工作階段以回答 Cursor 回傳的釐清問題,而不是卡住等待
  • 用 doctor 工具診斷設定問題
適用情境
適合讓前沿助理負責理解任務、撰寫說明與審閱變更,而由另一個 Cursor 命令列代理執行多檔案編輯;也適合希望實作環節使用 Cursor 模型額度而非其他訂閱的情況。
執行需求
以 stdio 方式在本機執行,通常透過 npx 啟動。需要 Node.js 20+ 以及已安裝並登入的 Cursor 命令列(cursor-agent login)。未宣告 API 金鑰或環境變數;各編輯器的設定方式不同。
安裝前請注意
被委派的代理會修改所指定工作目錄中的檔案,接受前應審閱差異。它依賴你既有的 Cursor 命令列登入與方案,用量可能計入 Cursor 模型額度。僅限桌面端,不提供網頁版。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Cursor Delegate,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

Cursor Delegate

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.

[npm version] [npm downloads] [MCP Registry] [cursor-delegate-mcp MCP server] [node] [license: MIT] [tests]

[Cursor Delegate logo]

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.


[Demo]

🧠 Frontier quality, kept

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.

⚡ Done faster

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.

🔋 Your limits stop being the bottleneck

Composer and Grok draw from the Cursor Models usage pool, separate from third-party model usage on supported Cursor plans. Your Claude or Codex subscription handles the brief and review while Cursor runs the implementation. If you pay per token on API, implementation moves onto the Cursor capacity you already have.

[You and your agent plan and review; the MCP delegate tool hands the brief to cursor-agent (Composer 2.5), which implements and edits your workspace; a clean result comes back with what changed, which files, and the plan, for your agent to review]

[Delegate result payload]

Features

  • 🤝 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 — plan mode: Cursor drafts a plan, you review it, then the same session implements it.
  • 🔍 Ask anything — ask mode: Q&A over your codebase.
  • 🩺 Self-diagnosing — a doctor tool 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, OpenCode, Antigravity, 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.

Install

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

Claude Code

shell
/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 — Claude writes the brief, Cursor grinds through the files, Claude walks you through the diff.

ChatGPT desktop / Codex

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

GitHub Copilot CLI

shell
copilot plugin install andreilungeanu/cursor-delegate-mcp

Any other MCP client

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

Client-specific config locations

VS Code — one-click install, or .vscode/mcp.json

[Install in VS Code] [Install in VS Code Insiders]

Or add it manually:

json
{  "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

Same mcpServers block as the generic snippet above. Cascade caps you at 100 tools across all servers.

Visual Studio 2022 / 2026 — %USERPROFILE%\.mcp.json

Same servers + type: "stdio" shape as VS Code. Requires Visual Studio 2026, or 2022 17.14+. Note the top-level key is servers, not mcpServers. Visual Studio also discovers .mcp.json next to the solution, plus .vscode/mcp.json.

OpenCode — ~/.config/opencode/opencode.json or project opencode.json

OpenCode does not use mcpServers. Local servers go under mcp, with type: "local" and command as one array:

json
{  "$schema": "https://opencode.ai/config.json",  "mcp": {    "cursor-delegate": {      "type": "local",      "command": ["npx", "-y", "cursor-delegate-mcp"],      "enabled": true    }  }}
Google Antigravity — ~/.gemini/config/mcp_config.json or workspace .agents/mcp_config.json

Same mcpServers block as the generic snippet above. In the IDE: … on the agent panel → MCP Servers → Manage MCP Servers → View raw config. Antigravity 2.0, IDE, and CLI share the Gemini config file. You may need to approve the server's tools on first run.

Kiro — .kiro/settings/mcp.json or ~/.kiro/settings/mcp.json

Same mcpServers block as the generic snippet above. Workspace file wins when both exist.

Kilo Code — kilo.jsonc (mcp key, not mcpServers)

Same shape as OpenCode: type: "local" and command as one array. In the VS Code extension: Settings → MCP → Add Server → Local (stdio). On Windows, if npx is not found, use command cmd with arguments /c, npx, -y, cursor-delegate-mcp.

Zed — Settings → AI → MCP Servers, or context_servers in Zed settings
json
{  "context_servers": {    "cursor-delegate": {      "command": "npx",      "args": ["-y", "cursor-delegate-mcp"],      "env": {}    }  }}

Zed's native agent uses this. External ACP agents in Zed read their own MCP config unless you forward Zed's servers.

License

MIT © Andrei Lungeanu

Technical reference · Security · Privacy · Terms · Changelog

來源:README.md,提交 78cadda

工具

3

delegate

Delegate coding task to Cursor

Delegate a coding task to cursor-agent over ACP. Never shell out to cursor-agent — use this tool only. Auto-approves every permission the agent requests, in any mode and anywhere on disk. Clarifying questions arrive as prose in result — resume with resumeSessionId to answer. Keep model (composer-2.5), fast and effort at their defaults unless the user explicitly asks. See the delegate skill.

輸入參數fastmodespec必填modeleffortcontextworkspace必填contextFilesresumeSessionId

cancel

Cancel Cursor delegation

Best-effort cancel of an in-flight delegation by sessionId. session/cancel is advisory — the agent may finish the turn anyway, and the delegate result then carries cancelRequested. Status: cancelled, killed (agent process observed to exit), not-running (turn already ended, still resumable), not-found (id not in this process's recent session history).

輸入參數forcesessionId必填

doctor

Diagnose Cursor delegation setup

Setup diagnostics: plugin version, MCP client capabilities, cursor-agent launcher resolution. Run when delegation fails or agent.found is false.

輸入參數deep

版本歷史

5
  1. v2.7.0Nov 7, 2026
  2. v2.6.0Oct 22, 2026
  3. v2.5.2Oct 15, 2026
  4. v2.4.0Oct 5, 2026
  5. v2.3.0Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分