Cursor · AI development environment
Product and access
Cursor is an AI-powered code editor and development environment. Agent modes and Cursor CLI are interfaces for the same product.
Provider
Anysphere develops Cursor as an AI development environment. Its offering combines an editor, local agents, CLI, cloud agents and tools for teams.
- Operator
- Anysphere, Inc.
- Organization
- Company
- Website
- cursor.com
Core features
10 features from provider sources · checked on 9 October 2026. Availability and limits are listed below.
Agent, Plan and Ask modes
Agent works on tasks with tools, Plan prepares implementation, and Ask explores the codebase in read-only mode.
Source 2MCP connections
MCP connects external data sources and tools; agents can use configured tools.
Source 4Terminal and file editing
The agent can edit files and run terminal commands; approval and execution follow the selected mode.
Source 1MCP approvals
MCP calls follow the selected Run Mode and its approval rules; Auto-review can approve calls using rules and an automated assessment.
Source 4Cursor CLI
The CLI supports agent tasks, session continuation, MCP, and the same project rules.
Source 2Hooks during agent runs
Scripts can add context at defined points, review or block actions, and log results.
Source 5Browser checks
The agent uses a browser and screenshots to inspect web interfaces and check changes.
Source 1Revert changes through checkpoints
Checkpoints restore earlier working states within an agent session.
Source 1
Requirements and limits
Requirement
Access and usage budget
Agent usage follows the plan, model and included usage budget. The current documentation distinguishes Cursor Models and Other Models as separate usage pools.
Source 6Requirement
Approve MCP tools
MCP access follows Run Mode, the allowlist and approval configuration. Check the tools actually permitted before use.
Source 4Limitation
Cloud hooks with narrower scope
Cloud agents do not support all local hooks: IDE session, MCP execution, and tab completion hooks, among others, do not run there.
Source 5Limitation
User hooks in the cloud
Cloud agents do not load hooks from the local user directory; project hooks must be configured in the repository.
Source 5
Operation & oversight
Operational details for this profile have not yet been researched.
Practical tasks
Editorial examples based on documented features. No product tests performed.
Narrow down the cause of a bug
- Your input
- Repository, reproduction steps, and project rules
- Possible result
- The agent investigates affected areas and proposes a limited correction.
- What to check
- Review the diff and targeted checks yourself.
Prepare a code change for an issue
- Your input
- Issue, codebase, and approved MCP project tools
- Possible result
- Agent plans the work and creates code changes in the project.
- What to check
- Check tool approvals, changes, and local behavior.
Investigate a reproducible error in a repository and prepare a small change with tests.
Your possible prompt
Read the project rules. Investigate [error], propose a small change, and run the relevant checks. Show me the diff and any remaining uncertainties.
Getting-started idea based on documented capabilities. Not an executed product test. Adapt the task, data, and permissions.
Setup and pricing
Setup
Open project and provide rules
Prices and included usage
Pricing checked
Subscription with an included model budget; additional usage is billed by consumption.
- Hobby
- USD 0 per month
Limited agent requests and access to Composer.
Price source - Pro
- USD 20 per month, excluding taxes
Higher agent limits, additional models, CLI and cloud agents.
Price source - Teams Standard
- USD 40 per user per month, excluding taxes
Team administration, shared context, Privacy Mode and SSO.
Price source - Enterprise
- Custom pricing
Pooled usage, SCIM, access controls and audit logs.
Price source
- The prices shown are the monthly USD prices on the public pricing page. Additional usage follows model pricing and, for team plans, may incur additional token fees.
Sources and evidence
Official agent, CLI, rules, MCP, hooks and model documentation checked. Some former docs.cursor.com paths lead only to the general overview; specific canonical sources are recorded. Agent, Plan and Ask are the currently documented CLI modes.
Editorial team: Michael Meierhoff · sources reviewed on . Provider information is not independent evidence of performance.
-
cursor.com /docs/agent/overview
-
cursor.com /docs/cli/overview
-
cursor.com /docs/rules
-
cursor.com /docs/mcp
-
prod.cursor.com /docs/hooks
-
cursor.com /docs/models-and-pricing
-
cursor.com /docs/agent/plan-mode
