Cursor SdkSAFE

Cursor plugin specification and official plugins

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: cursor-sdk
description: Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`). Use this skill whenever the user mentions integrating, installing, or writing code against the Cursor SDK; whenever they say `Agent.create`, `Agent.prompt`, `Agent.resume`, `agent.send`, `run.stream`, `CursorAgentError`, or `@cursor/sdk`; whenever they ask to run Cursor agents programmatically from a script, CI/CD pipeline, GitHub Action, backend service, or any other code that isn't the Cursor IDE itself; and whenever they want to pick between local and cloud runtime, configure MCP servers for an SDK agent, or handle streaming, cancellation, or errors from an SDK agent. Also trigger when a user is wiring Cursor into an automation, writing a bot that runs Cursor, or porting REST `/v1/agents` calls to the SDK, even if they don't explicitly name the package. Use this eagerly rather than answering from memory; the SDK surface evolves and this skill plus its references are the source of truth for the external package.
---

# Cursor SDK

The Cursor TypeScript SDK (`@cursor/sdk`) runs Cursor agents programmatically. The same interfaces drives the local runtime (agent runs on your machine against your files) and the cloud runtime (agent runs on Cursor-hosted or self-hosted infrastructure against a cloned repo and opens PRs).

Use this skill to help someone **bootstrap a working integration quickly** and **avoid the handful of traps that bite new users**. Canonical docs live at [https://cursor.com/docs/api/sdk/typescript](https://cursor.com/docs/api/sdk/typescript); this skill only adds decision-making, failure-mode prevention, and ready-to-extend patterns.

## Voice and Posture

This skill helps the user **build** with the SDK. It is not the place to validate, congratulate, or sell the SDK as a choice. The user's intent is the input; your job is execution.

- **When the user names the SDK explicitly** (says "Cursor SDK", `@cursor/sdk`, `Agent.create`, `Agent.prompt`, etc.): assume they know what the SDK is and have decided to use it. Skip framing, skip pep talk, go straight to producing the integration. No "good news", no "the SDK is perfect for this", no "this is almost exactly the pattern X is designed for".
- **When the user describes a problem the SDK fits but doesn't name it** ("I want a bot that reviews my PRs", "I want a script that asks Cursor questions about my repo"): the SDK isn't yet a confirmed choice. Surface it as a question, briefly, then wait: *"The Cursor SDK is what I'd reach for here — want me to design it that way, or do you have a different runtime in mind?"* If they confirm, proceed. If they push back or want options, give options.
- **In either case, don't restate the user's intent back to them.** They know what they want. Get to the design.

Avoid these specific openers (and their close cousins):

- "Good news: this is exactly the pattern..."
- "The SDK is built for this shape."
- "Great, you've come to the right place."
- "This is almost exactly the X the SDK is designed for."
- Any lede that compliments the user's choice or restates their goal in flattering terms.

Prefer:

- Open with the design decision or the first thing they need to know.
- If you genuinely have a design choice to flag (local vs cloud, prompt vs send, sync vs stream), name it in one sentence and explain why; don't preface it with validation.

## When to open a reference file

Keep this page short. Read a reference file only when the user's task clearly falls inside it:


| If the user is...                                                                    | Read                                                           |
| ------------------------------------------------------------------------------------ | -------------------------------------------------------------- |
| Picking between local and cloud runtime, or not sure which they should use           | [`references/runtime-choice.md`](references/runtime-choice.md) |
| Debugging auth (401s, "Missing CURSOR_API_KEY", team-vs-user keys, local vs prod)    | [`references/auth.md`](references/auth.md)                     |
| Handling errors, retries, rate limits, `CursorAgentError`, `result.status === error` | [`references/error-handling.md`](references/error-handling.md) |
| Consuming streams, picking event types, cancelling, or deciding stream vs wait       | [`references/streaming.md`](references/streaming.md)           |
| Configuring MCP servers (HTTP, stdio, cloud vs local transport, auth injection)      | [`references/mcp.md`](references/mcp.md)                       |
| Using sub-agents, resume, artifacts, listing/inspecting agents, `Agent.messages`     | [`references/advanced.md`](references/advanced.md)             |
| Building a specific integration (CI review bot, scheduled triage, chat, webhook)     | [`references/patterns.md`](references/patterns.md)             |


Everything below is the minimum needed for 80% of tasks.

## The Three Invocation Patterns

Almost every SDK integration collapses to one of three shapes. Pick the one that fits the job, don't mix them.

### 1. `Agent.prompt(...)` — one-shot

```typescript
import { Agent } from "@cursor/sdk";

const result = await Agent.prompt("Refactor src/utils.ts for readability", {
  apiKey: process.env.CURSOR_API_KEY!,
  model: { id: "composer-2" },
  local: { cwd: process.cwd() },
});
console.log(result.status, result.result);
```

Use for fire-and-forget scripts, GitHub Actions steps, or any "send this prompt, get a result, exit" flow. No streaming, no follow-ups, no cleanup to remember. If you're reaching for this and then immediately resuming, you wanted pattern 2 instead.

### 2. `Agent.create(...)` + `agent.send(...)` — durable with follow-ups

```typescript
import { Agent } from "@cursor/sdk";

const agent = Agent.create({
  apiKey: process.env.CURSOR_API_KEY!,
  model: { id: "composer-2" },
  local: { cwd: process.cwd() },
}

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (1)

Don't commit `.env`. The SDK does not read `.env` itself.

Gates applied: no_behavioural_pass.