# Cursor

Coding agent for understanding code, planning changes, developing, and testing.

Canonical profile: https://agenten-kompass.mmeierhoff.chatgpt.site/en/agents/cursor/
Editor: [Michael Meierhoff](https://agenten-kompass.mmeierhoff.chatgpt.site/en/about/)
Sources reviewed: 2026-09-30
Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests.

## Overview

Cursor is an AI-powered code editor and development environment. Agent modes and Cursor CLI are interfaces for the same product.

- Provider: Cursor
- Product family: Cursor
- Profile type: AI development environment
- Environment: Editor, CLI and cloud agents
- Connections: Repositories, terminal and MCP
- Setup: Open project and provide rules
- Pricing model: Plan / model usage

## Key features

### Agent, Ask and Manual modes

Modes range from autonomous multi-part work to focused editing or read-only exploration.

Source: https://docs.cursor.com/agent

### Project rules

Rules in .cursor/rules provide reusable, project-specific guidance.

Source: https://docs.cursor.com/context/rules-for-ai

### MCP connections

MCP connects external data sources and tools; agents can use configured tools.

Source: https://docs.cursor.com/context/model-context-protocol

### Code and web search

Agent tools support searching the codebase and web sources.

Source: https://docs.cursor.com/en/agent/tools

### Terminal and file editing

The agent can edit files and run terminal commands; approval and execution follow the selected mode.

Source: https://docs.cursor.com/en/agent/tools

### MCP approvals

MCP calls require approval by default; Auto-run changes this behavior.

Source: https://docs.cursor.com/context/model-context-protocol

### Cursor CLI

The CLI supports agent tasks, session continuation, MCP, and the same project rules.

Source: https://docs.cursor.com/en/cli/using

### Hooks during agent runs

Scripts can add context at defined points, review or block actions, and log results.

Source: https://prod.cursor.com/docs/hooks

## Requirements and limits

### Access and usage budget

Requirement: Cursor offers a free entry point and paid plans; agent usage is billed by model and included usage budget.

Source: https://docs.cursor.com/account/pricing

### Approve MCP tools

Requirement: MCP calls require approval by default; automatic execution must be explicitly enabled.

Source: https://docs.cursor.com/context/model-context-protocol

### Cloud hooks with narrower scope

Limitation: Cloud agents do not support all local hooks: IDE session, MCP execution, and tab completion hooks, among others, do not run there.

Source: https://prod.cursor.com/docs/hooks

### User hooks in the cloud

Limitation: Cloud agents do not load hooks from the local user directory; project hooks must be configured in the repository.

Source: https://prod.cursor.com/docs/hooks

## Example workflows

### 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.

## Context

Review code, tests, and changes. Specific access depends on the environment, plan, and project configuration.

Cursor documentation reviewed. Agent modes, plan features, hooks, and MCP are documented; available models, quotas, and some hook types differ between the local IDE and cloud agent.

## Sources

- https://cursor.com/docs/agent/overview

- https://docs.cursor.com/agent

- https://docs.cursor.com/context/rules-for-ai

- https://docs.cursor.com/context/model-context-protocol

- https://docs.cursor.com/en/agent/tools

- https://docs.cursor.com/en/cli/using

- https://prod.cursor.com/docs/hooks

- https://docs.cursor.com/account/pricing

- https://prod.cursor.com/docs/agent/plan-mode

[Sources and method](https://agenten-kompass.mmeierhoff.chatgpt.site/en/sources/)