Skip to content

Guide

Cursor SDK Agents Guide

By The Learn Cursor Editorial TeamUpdated 3 sections

Answer first

Cursor's June 2026 SDK update added TypeScript and Python support for custom tools, local auto-review, JSONL and custom stores, nested subagents, request IDs and reliability fixes for local and cloud agent apps.

Cover image for Cursor SDK Agents Guide

What changed in Cursor SDK, June 2026?

Cursor's June 2026 SDK update added TypeScript and Python support for custom tools, local auto-review, JSONL and custom stores, nested subagents, request IDs and reliability fixes for local and cloud agent apps.

Release fact
Custom tools
Why it matters
local.customTools exposes your functions through the built-in custom-user-tools MCPModel Context Protocol. A standard that lets an AI agent pull in context from outside the repo, like Jira tickets or internal docs. server.
Release fact
Auto-review
Why it matters
local.autoReview routes local tool calls through a classifier rather than bypassing review.
Release fact
Stores
Why it matters
SQLite, JSONL and custom LocalAgentStore choices support durable agent state.
Release fact
Nested subagents
Why it matters
Custom tools are visible through subagents, and subagents can nest for delegated work.
Release fact
Request IDs
Why it matters
Run metadata can carry request IDs for support and debugging.

Release facts checked on 2026-06-23. Use the linked Cursor sources before quoting product mechanics in a live customer, security or pricing conversation.

How should a team use Cursor SDK agents?

  1. 1Define one SDK agent job with explicit input, output and owner.
  2. 2Expose only the product functions the job needs as custom tools.
  3. 3Choose SQLite, JSONL or a custom store based on audit and retention needs.
  4. 4Use auto-review and request IDs so headless runs stay inspectable.
Release-to-workflow map

Interactive diagram. Use Tab to move through hotspots or use the step controls when shown.

Step 1Step 2Step 3Step 4▲ GATE
1/4
Step 1: Define one SDK agent job with explicit input, output and owner.

What should stay bounded?

Guardrail

Validate custom-tool inputs as if the model were an untrusted caller.

Guardrail

Do not persist secrets or full transcripts when a summary is enough.

Guardrail

Use auto-review as a gate, not as proof that a human review is unnecessary.

Frequently asked questions

Who is Cursor SDK Agents Guide for?

AI engineers and platform teams building internal tools, CI agents or product workflows on the Cursor SDK.

What makes this page credible?

The guide cites Cursor's June 4, 2026 SDK changelog and maps custom tools, stores and auto-review to safe programmatic-agent design.

What should I do next?

Start with one real repo task, capture the prompt and review the result before scaling the workflow.

Editorial notes

Source review

Last checked
June 23, 2026
Scope
Cursor docs, Cursor Learn pages and product docs.
Refresh
Quarterly, plus changes to Cursor agent or CLI docs.
Reviewer
Learn Cursor editorial

Page assets

Primary media
Workflow diagram.
Supporting media
Learn Cursor practice screenshot.
Interactive element
Step diagram.
Transcript
Add a transcript when a recorded walkthrough is added.
Refresh owner
Learn Cursor editorial.

Content pod

Pod
Workflow pod
Owner
Editorial director
Reviewers
DevRel engineer, SEO lead, Senior editor

QA gate

Human signal
Includes a task-specific diagram, checklist or calculator.
Claims
Claims stay tied to sources, visible limits and page scope.
Visual proof
Uses product screenshots or annotated workflow diagrams, not stock art.
Page rhythm
Sections vary between answer, method, visual and action blocks.

Sources & last verified

Cursor ships frequently. Facts verified against primary sources on June 23, 2026.

Keep reading