• Tech Dev NotesTech Dev Notes
Apps
  • App lookup
  • App compare
Market movement
  • App charts
  • App rankings
Visual proof
  • App screens
  • App listing screenshots
  • App icons
Build intelligence
  • App tech stacks
  • Tool releases
  • Developers
More
  • X feature flags
  • Grokipedia
  • Blog
  • Follow on X
Skip to content
All content/ filesChangelog

cursor-docs/latest/content · Jun 26, 20:20 UTC

pages/cli/reference/parameters.txt

TXT·6.9 KB·256 lines

content/

  • pages

    • api.txt
    • approval-agents.txt
    • bugbot.txt
    • cloud-agent.txt
    • customize-cursor.txt
    • enterprise.txt
    • evals.txt
    • extension-api.txt
    • hooks.txt
    • mcp.txt
    • models-and-pricing.txt
    • plugins.txt
    • rules.txt
  • pages/account

    • regions.txt
    • update-access.txt
  • pages/account/enterprise

    • billing-groups.txt
    • cyber-safeguards.txt
    • service-accounts.txt
  • pages/account/organizations

    • organization-admin-api.txt
  • pages/account/pricing

    • request-based-legacy.txt
  • pages/account/teams

    • admin-api.txt
    • ai-code-tracking-api.txt
    • analytics-api.txt
    • analytics.txt
    • dashboard.txt
    • members.txt
    • pricing.txt
    • scim.txt
    • setup.txt
    • sso.txt
  • pages/agent

    • agent-review.txt
    • agents-window.txt
    • debug-mode.txt
    • design-mode.txt
    • overview.txt
    • plan-mode.txt
    • prompting.txt
    • security.txt
  • pages/agent/security

    • run-modes.txt
  • pages/agent/tools

    • browser.txt
    • canvas.txt
    • search.txt
    • terminal.txt
  • pages/cli

    • acp.txt
    • changelog.txt
    • github-actions.txt
    • headless.txt
    • installation.txt
    • mcp.txt
    • overview.txt
    • shell-mode.txt
    • using.txt
  • pages/cli/reference

    • authentication.txt
    • configuration.txt
    • output-format.txt
    • parameters.txt
    • permissions.txt
    • slash-commands.txt
    • terminal-setup.txt
  • pages/cloud-agent

    • automations.txt
    • best-practices.txt
    • capabilities.txt
    • choose-runtime.txt
    • my-machines.txt
    • private-workers.txt
    • security-network.txt
    • self-hosted-cloud-run.txt
    • self-hosted-k8s.txt
    • self-hosted-pool.txt
    • settings.txt
    • setup.txt
  • pages/cloud-agent/api

    • endpoints.txt
    • webhooks.txt
  • pages/configuration

    • worktrees.txt
  • pages/configuration/migrations

    • vscode.txt
  • pages/cursor-review

    • merge-queue.txt
    • overview.txt
    • pr-inbox.txt
    • pr-page.txt
  • pages/cursor-review/cli

    • authentication.txt
    • parameters.txt
    • stacking.txt
  • pages/customizing

    • aws-bedrock.txt
  • pages/enterprise

    • baa.txt
    • compliance-and-monitoring.txt
    • deployment-patterns.txt
    • endpoint-security.txt
    • identity-and-access-management.txt
    • llm-safety-and-controls.txt
    • model-and-integration-management.txt
    • network-configuration.txt
    • organization-groups.txt
    • organizations.txt
    • pooled-usage.txt
    • privacy-and-data-governance.txt
    • private-connectivity.txt
    • security-hardening.txt
  • pages/get-started

    • quickstart.txt
  • pages/integrations

    • azure-devops.txt
    • bitbucket.txt
    • cursor-blame.txt
    • github.txt
    • gitlab.txt
    • jetbrains.txt
    • jira.txt
    • linear.txt
    • microsoft-teams.txt
    • notion.txt
    • slack.txt
    • xcode.txt
  • pages/mcp

    • install-links.txt
  • pages/models

    • claude-4-5-haiku.txt
    • claude-4-5-sonnet.txt
    • claude-4-6-sonnet.txt
    • claude-4-sonnet-1m.txt
    • claude-4-sonnet.txt
    • claude-fable-5.txt
    • claude-opus-4-5.txt
    • claude-opus-4-6-fast.txt
    • claude-opus-4-6.txt
    • claude-opus-4-7-fast.txt
    • claude-opus-4-7.txt
    • claude-opus-4-8.txt
    • cursor-composer-1-5.txt
    • cursor-composer-1.txt
    • cursor-composer-2-5.txt
    • cursor-composer-2.txt
    • gemini-2-5-flash.txt
    • gemini-3-1-pro.txt
    • gemini-3-5-flash.txt
    • gemini-3-flash.txt
    • gemini-3-pro-image-preview.txt
    • gemini-3-pro.txt
    • glm-5-2.txt
    • gpt-5-1-codex-max.txt
    • gpt-5-1-codex-mini.txt
    • gpt-5-1-codex.txt
    • gpt-5-2-codex.txt
    • gpt-5-2.txt
    • gpt-5-3-codex.txt
    • gpt-5-4-mini.txt
    • gpt-5-4-nano.txt
    • gpt-5-4.txt
    • gpt-5-5.txt
    • gpt-5-codex.txt
    • gpt-5-fast.txt
    • gpt-5-mini.txt
    • gpt-5.txt
    • grok-4-20.txt
    • grok-4-3.txt
    • grok-build-0-1.txt
    • kimi-k2-5.txt
  • pages/reference

    • deeplinks.txt
    • ignore-file.txt
    • keyboard-shortcuts.txt
    • permissions.txt
    • plugins.txt
    • sandbox.txt
    • third-party-hooks.txt
  • pages/sdk

    • python.txt
route: /docs/cli/reference/parameters
title: Parameters
description: Learn about Cursor CLI command parameters and options.

Parameters
Global options
Global options can be used with any command:
Option
Description
-v, --version
Output the version number
--api-key <key>
API key for authentication (can also use CURSOR_API_KEY env var)
-H, --header <header>
Add custom header to agent requests (format: Name: Value, can be used multiple times)
-p, --print
Print responses to console (for scripts or non-interactive use). Has access to all tools, including write and shell.
--output-format <format>
Output format (only works with --print): text, json, or stream-json (default: text)
--stream-partial-output
Stream partial output as individual text deltas (only works with --print and stream-json format)
--resume [chatId]
Resume a chat session
--continue
Continue the previous session (alias for --resume=-1)
--model <model>
Model to use
--mode <mode>
Set agent mode: plan or ask (agent is the default when no mode is specified)
--plan
Start in plan mode (shorthand for --mode=plan)
--list-models
List all available models
-f, --force
Force allow commands unless explicitly denied
--yolo
Alias for --force
--sandbox <mode>
Set sandbox mode: enabled or disabled
--approve-mcps
Automatically approve all MCP servers
--trust
Trust the workspace without prompting (headless mode only)
--workspace <path>
Workspace directory to use
--plugin-dir <path>
Load a local plugin directory (can be specified multiple times)
-w, --worktree [name]
Run in a new Git worktree under ~/.cursor/worktrees/<reponame>/<name>. If omitted, a name is generated.
--worktree-base <branch>
Branch or ref to base the new worktree on (default: current HEAD)
--skip-worktree-setup
Skip running worktree setup scripts from .cursor/worktrees.json
-h, --help
Display help for command
Commands
Command
Description
Usage
agent [prompt...]
Start in agent mode (the default)
agent agent "fix the tests"
login
Authenticate with Cursor
agent login
logout
Sign out and clear stored authentication
agent logout
status | whoami
View authentication status
agent status
about
Display version, system, and account info
agent about
models
List available models for this account
agent models
mcp
Manage MCP servers
agent mcp
sandbox
Configure sandbox mode or run one command in a sandbox (hidden)
agent sandbox enable
worker
Start a private cloud worker that runs agents in your environment
agent worker start
acp
Start ACP server mode (advanced, hidden command)
agent acp
update
Update Cursor Agent to the latest version
agent update
ls
Resume a chat session
agent ls
resume
Resume the latest chat session
agent resume
create-chat
Create a new empty chat and return its ID
agent create-chat
generate-rule | rule
Generate a new Cursor rule with interactive prompts
agent generate-rule
install-shell-integration
Install shell integration to ~/.zshrc
agent install-shell-integration
uninstall-shell-integration
Remove shell integration from ~/.zshrc
agent uninstall-shell-integration
help [command]
Display help for command
agent help [command]
agent acp is intended for custom ACP clients and advanced integrations. It is
hidden from default command help output.
When no command is specified, Cursor Agent starts in interactive agent mode by
default.
MCP
Manage MCP servers configured for Cursor Agent.
Subcommand
Description
Usage
login <identifier>
Authenticate with an MCP server configured in .cursor/mcp.json or ~/.cursor/mcp.json
agent mcp login <identifier>
list
List configured MCP servers and their status
agent mcp list
list-tools <identifier>
List available tools and their argument names for a specific MCP
agent mcp list-tools <identifier>
enable <identifier>
Add an MCP server to the local approved list
agent mcp enable <identifier>
disable <identifier>
Disable an MCP server so it won't load or prompt for approval
agent mcp disable <identifier>
All MCP commands support -h, --help for command-specific help.
Sandbox
Configure sandbox mode or run one command in a sandbox.
Subcommand
Description
Usage
enable
Enable sandbox mode for command execution
agent sandbox enable
disable
Disable sandbox mode and use allowlist mode
agent sandbox disable
reset
Reset sandbox configuration to defaults
agent sandbox reset
run <cmd> [args...]
Run a command in a sandbox with workspace read/write
agent sandbox run ls
help [command]
Display help for command
agent sandbox help
Command
Option
Description
sandbox run
--allow-paths <paths>
Comma-separated list of extra read/write paths
sandbox run
--readonly-paths <paths>
Comma-separated list of extra read-only paths
sandbox run
--blocked-patterns <patterns>
Comma-separated list of gitignore-style patterns to block
sandbox run
--sandbox
Run with the workspace read/write sandbox policy (default: true)
sandbox run
--network
Enable network access in the sandbox (default: false)
sandbox run
--sb-debug
Write sandbox debug logs to a temp folder and print the path
All sandbox commands support -h, --help for command-specific help.
Worker
Start a private cloud worker that connects to Cursor and runs agents in your environment.
Subcommand
Description
Usage
start
Start the worker and connect to Cursor
agent worker start
debug
Run private worker preflight diagnostics for auth, privacy, and routing
agent worker debug
help [command]
Display help for command
agent worker help
Command
Option
Description
worker
--auth-token-file <path>
Path to a file containing the worker auth token
worker
--worker-dir <path>
Workspace root to expose to agents. Repeatable. The first value is the assignment identity.
worker
--management-addr <address>
Listen address for /healthz, /readyz, and /metrics
worker
--label <key=value>
Add a worker label. Can be used multiple times. Can't be used with --labels-file.
worker
--labels-file <path>
Path to a JSON or TOML labels file. Can also use CURSOR_WORKER_LABELS_FILE.
worker
--idle-release-timeout <seconds>
Seconds the worker may stay connected after becoming idle. Default 0 disables idle-based release.
worker
--pool
Register for pool assignment. One cloud agent claims the worker at a time.
worker
--single-use
Legacy alias for --pool
worker
--pool-name <name>
Pool label for pool workers. Requires --pool or --single-use. Defaults to default.
worker
--name <name>
Custom display name. Defaults to the machine hostname.
worker
--data-dir <path>
Base directory for logs, artifacts, and recording data
worker
--debug
Print worker debug diagnostics before starting bridge mode
worker start
--verbose
Enable verbose startup logs
worker debug
--json
Output the debug report as JSON
Command-specific options
Command
Option
Description
status, whoami
--format <format>
Output format: text or json (default: text)
about
--format <format>
Output format: text or json (default: text)
Arguments
When starting in chat mode (default behavior), you can provide an initial prompt:
Arguments:
prompt — Initial prompt for the agent
Getting help
All commands support the global -h, --help option to display command-specific help.
Previouspages/cli/reference/output-format.txtNextpages/cli/reference/permissions.txt

© 2026 Tech Dev Notes

RSSAboutAPIPrivacyTermsSitemap@techdevnotes