Cursor CLI reference - Subcommands
Cursor CLI commands and subcommands
Cursor CLI documents 42 subcommands, including agent [prompt...], login and logout. These run as cursor-agent <command> from your shell. Each row gives the docs' description, accepted values and an example where one is documented.
Last verified 7 official pagesFull Cursor CLI reference
| Command | Description | Example |
|---|---|---|
agent [prompt...] | Starts in agent mode, the default. When no command is specified, Cursor Agent starts in interactive agent mode; an initial prompt can be passed as an argument. prompt: initial prompt for the agent Docs: agent [prompt...] | agent "refactor the auth module to use JWT tokens" |
login | Authenticates with Cursor using a browser flow and stores credentials locally. During login, pressing q reveals a QR code for the same login URL. Docs: login | agent login |
logout | Signs out and clears stored authentication. Docs: logout | agent logout |
status | whoami | Views authentication status: whether you are authenticated, account information, and current endpoint configuration. --format text|json Docs: status | whoami | agent status |
about | Displays version, system, and account info. --format text|json Docs: about | agent about |
models | Lists available models for this account, including team Bedrock models and respecting team model restrictions. Docs: models | agent models |
mcp | Manages MCP servers configured for Cursor Agent. MCP in the CLI uses the same configuration as the editor. login | list | list-tools | enable | disable Docs: mcp | agent mcp |
mcp login <identifier> | Authenticates with an MCP server configured in .cursor/mcp.json or ~/.cursor/mcp.json, with automatic callback handling. identifier Docs: mcp login <identifier> | agent mcp login <identifier> |
mcp list | Lists configured MCP servers and their status in an interactive menu showing names, connection status, configuration source, and transport. Docs: mcp list | agent mcp list |
mcp list-tools <identifier> | Lists available tools and their argument names for a specific MCP server. identifier Docs: mcp list-tools <identifier> | agent mcp list-tools playwright |
mcp enable <identifier> | Adds an MCP server to the local approved list. identifier Docs: mcp enable <identifier> | agent mcp enable <identifier> |
mcp disable <identifier> | Disables an MCP server so it will not load or prompt for approval. identifier Docs: mcp disable <identifier> | agent mcp disable <identifier> |
sandbox | Configures sandbox mode or runs one command in a sandbox. Hidden command. enable | disable | reset | run | help Docs: sandbox | agent sandbox enable |
sandbox enable | Enables sandbox mode for command execution. Docs: sandbox enable | agent sandbox enable |
sandbox disable | Disables sandbox mode and uses allowlist mode. Docs: sandbox disable | agent sandbox disable |
sandbox reset | Resets sandbox configuration to defaults. Docs: sandbox reset | agent sandbox reset |
sandbox run <cmd> [args...] | Runs a command in a sandbox with workspace read/write. --allow-paths, --readonly-paths, --blocked-patterns, --sandbox, --network, --sb-debug Docs: sandbox run <cmd> [args...] | agent sandbox run ls |
sandbox help [command] | Displays help for a sandbox command. Docs: sandbox help [command] | agent sandbox help |
worker | Starts a private cloud worker that connects to Cursor and runs agents in your environment. start | debug | controller | help Docs: worker | agent worker start |
worker start | Starts the worker and connects to Cursor. Waits for the bridge to connect before reporting ready. --verbose Docs: worker start | agent worker [options] start |
worker debug | Runs private worker preflight diagnostics for auth, privacy, and routing. --json Docs: worker debug | agent worker debug |
worker help [command] | Displays help for a worker command. Docs: worker help [command] | agent worker help |
worker controller | Starts workers from a --spawn hook, either claim-then-spawn (default) or as a warm pool with --warm-idle. Authenticates with a service account key. --spawn, --api-key, --pool, --all-pools, --warm-idle, --session-token, --identity-audience, --repository, --endpoint Docs: worker controller | agent worker controller --spawn ./spawn.sh --api-key "$CURSOR_API_KEY" --pool my-pool --pool default |
acp | Starts ACP (Agent Client Protocol) server mode over stdio with JSON-RPC 2.0, newline-delimited. Intended for custom clients and advanced integrations; hidden from default help output. Docs: acp | agent acp |
update | Updates Cursor Agent to the latest version. The CLI also tries to auto-update by default. Docs: update | agent update |
ls | Opens previous chats so you can resume one. Docs: ls | agent ls |
resume | Resumes the latest chat session. Docs: resume | agent resume |
create-chat | Creates a new empty chat and returns its ID. Docs: create-chat | agent create-chat |
generate-rule | rule | Generates a new Cursor rule with interactive prompts. Docs: generate-rule | rule | agent generate-rule |
install-shell-integration | Installs shell integration to ~/.zshrc. Docs: install-shell-integration | agent install-shell-integration |
uninstall-shell-integration | Removes shell integration from ~/.zshrc. Docs: uninstall-shell-integration | agent uninstall-shell-integration |
help [command] | Displays help for a command. Docs: help [command] | agent help [command] |
bedrock | Configures AWS Bedrock access with your own access keys or a team IAM role; works across interactive, headless, and editor sessions. Docs: bedrock | -no example |
persist | Starts a persistent session that keeps the agent running after you disconnect. Detach with /detach. attach | list | stop; --resume Docs: persist | -no example |
persist attach | Reconnects to a persistent session later. Docs: persist attach | -no example |
persist list | Lists persistent sessions (documented as agent persist list|stop for managing sessions). Docs: persist list | -no example |
persist stop | Stops a persistent session (documented as agent persist list|stop for managing sessions). Docs: persist stop | -no example |
env deploy | Deploys a Cloud Agent environment from an environment file. Files can include comments and trailing commas; invalid files fail with a syntax error pointing to where parsing stopped. environment file Docs: env deploy | -no example |
plugin marketplace add <git-url> | Registers a plugin marketplace from the shell without an interactive session. Pin a branch, tag, or commit with --git-ref. git URL; --git-ref Docs: plugin marketplace add <git-url> | -no example |
plugin marketplace list | Prints each marketplace's name, scope, and git URL. --format json for scripts Docs: plugin marketplace list | -no example |
plugin marketplace update | Re-indexes a marketplace from its repository. Docs: plugin marketplace update | -no example |
plugin marketplace remove | Deletes a user-scoped marketplace. Docs: plugin marketplace remove | -no example |
The rest of the Cursor CLI reference
FAQ
How many subcommands does Cursor CLI have?
The official Cursor CLI docs list 42 subcommands, including agent [prompt...], login and logout. All of them are in the table above, in the docs' order.
What does agent [prompt...] do in Cursor CLI?
Starts in agent mode, the default. When no command is specified, Cursor Agent starts in interactive agent mode; an initial prompt can be passed as an argument. Values: prompt: initial prompt for the agent. Example: agent "refactor the auth module to use JWT tokens"
Where are Cursor CLI subcommands documented?
On 7 official docs pages at cursor.com, last read on October 17, 2026. Every row in the table links the exact section it came from.
More on Cursor CLI
- Cursor CLI in the tools directoryWhat it is, who makes it and how it fits next to other coding agents.
- Cursor CLI errors and fixes18 error messages, quoted verbatim, with the documented fix for each.
- Cursor usage limitsPlan and tier limits for this tool, copied from the official docs.
Use other models in Cursor CLI
Setup guides from the model-in-tool directory, each with the env vars and base URL from official docs.
Sources
Last verified . Names and examples are copied verbatim from the 7 official pages below, and every row above links the exact section it came from.
Newsletter
Know when your tools change
One email per week. New coding agent releases, the flags and commands they add, and what they mean for how you work.