> ## Documentation Index > Fetch the complete documentation index at: https://docs.guardway.ai/llms.txt > Use this file to discover all available pages before exploring further. # Cursor > How Guardway governs Cursor on the device, what its hooks cover, what the Cursor posture card shows, and the limits. ## What this is for Guardway governs Cursor on each developer's machine, not by routing its traffic through your gateway. This covers both the Cursor app and the Cursor CLI. The Guardway agent works through Cursor's own hooks and reads Cursor's settings, and the results show in the console under **Endpoint AI Risk**, on each machine's detail. ## Why Cursor is not routed Cursor can't be routed through a Guardway gateway: * Cursor sends its requests through Cursor's servers, even when you use your own API keys. * The **Override OpenAI Base URL** setting is per user. Tab never uses it, and Agent and Auto can ignore it. * The Cursor CLI's proxy settings only front Cursor's own API. So [Posture](/discovery/endpoint-ai-policy#posture) does not apply to Cursor. Guardway governs it on the device instead. ## What Guardway covers through Cursor hooks Wherever Cursor is installed, the agent adds its entries to Cursor's hook file. Your own hooks in the same file are left as they are, and the entries are removed when the agent is uninstalled. | Area | What you get | | - | - | | **Live guard** | Each shell command or MCP call Cursor's agent is about to make is checked before it runs. With **Block**, the blocking rules stop it. See [Live guard](/discovery/endpoint-ai-policy#live-guard). | | **Usage** | Tokens and model for each turn in the app, priced at catalog rates. See [Usage and Cost](/discovery/guardway-cli/usage-and-cost#cursor). | | **Sessions and Behavior** | Cursor sessions, prompts sent, and shell and MCP calls, feeding the [Behavior](/discovery/endpoint-ai-policy#behavior) rules. | | **Subagents** | Subagent runs are recorded with their session. | | **MCP allowlist** | **MCP server not on the approved list** (`GOV-MCP-UNLISTED`) flags a call to an MCP server your organization did not approve. You can pin an approved server to its address or command, so an unapproved server can't reuse its name. | | **Secrets in edits** | **Agent wrote a credential into a file** (`BEHAV-SECRET-IN-EDIT`) flags a Cursor agent edit that put an API key, token or private key into a file. | | **Sandbox** | Whether Cursor can sandbox commands on the machine, and how many of the week's shell commands ran sandboxed. | | **Hook health** | Whether the hooks are wired and firing, and a warning when a Cursor update silenced a hook or changed what it sends. | ## Cursor posture The **Cursor posture** card on a machine's detail shows how Cursor is set up there. It is read from Cursor on the machine. Guardway never changes these settings. * **IDE run mode:** Ask every time, Allowlist, Auto-review or Run everything. A warning shows when Cursor runs agent commands without asking. * **Privacy mode:** the privacy mode Cursor is set to. * **Team:** locked to your team by device policy, signed in to a team but not locked, or no team. * **Own API keys:** which providers have a key in use, and which have a key saved but not in use. * **Unapproved endpoint:** flagged when Cursor Chat sends to an endpoint that is not your gateway or an approved host. When no approved list is known, the card shows a neutral custom endpoint note instead. * **Team settings:** own API keys disabled by your Cursor team, and the models your Cursor team allows and blocks. * **permissions.json:** what the file allows, shown read only. Guardway never writes this file. * **CLI sessions:** Cursor CLI sessions running at the last scan, including those started with `--force`, which run every command without asking. ## Prompt previews Prompt previews are off by default. Turn on **Keep Cursor prompt previews** in the policy's [Telemetry](/discovery/endpoint-ai-policy#telemetry) section to keep the first 240 bytes of each prompt typed in Cursor, redacted on the machine. It needs **Send Claude Code and Cursor usage to Guardway** on. Claude Code prompts are never sent. ## Limits * The Cursor CLI sends no token usage, subagent or prompt hooks. Its sessions show, but its usage is missing from cost, not zero. * Cloud agents run on Cursor's servers, so the agent on the machine does not see them. * Cost is an estimate at list prices. Cursor bills some usage from plan allowances. * Model limits are set in Cursor's own admin settings. Guardway shows them; it does not set them. ## Related Live guard, Behavior, Telemetry and AI Control settings. How each AI tool's usage and cost are measured. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.