record
AI agents invoke record to trigger actions in Windows Computer Use. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Given the server context (Windows desktop control, screen capture, play-testing), 'record' most likely captures screen/input recording sessions, which is an Execute-level operation with potential privacy implications. However, the empty description significantly reduces confidence. It could also mean recording macros or sessions for replay.
From the tool's definition Tool name is 'record'; description is empty and uninformative. Sibling tools include 'act', 'play', 'process', 'screenshot', 'system', 'window' on a server that provides full Windows desktop control with screen capture and input injection.
Attacks that exploit this kind of access
record. It is categorised as a Execute tool in the Windows Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Windows Computer Use MCP server in PolicyLayer and add a rule for record: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Windows Computer Use. Nothing to install.
record is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the record rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for record. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
record is provided by the Windows Computer Use MCP server (sshh12/windows-computer-use-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →