Write text to the clipboard. Requires the
AI agents use write_clipboard to create or update resources in Computer Use Windows — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Computer Use Windows environment.
This tool creates or modifies data (clipboard contents) in a reversible manner. While clipboard modification is generally low-risk in isolation, the medium severity reflects the context that clipboard content can be leveraged for secondary attacks (e.g., if an agent overwrites clipboard with malicious data intended for user paste, or replaces legitimate data).
From the tool's definition Tool name is 'write_clipboard' and description states 'Write text to the clipboard.' The verb 'Write' and the action of modifying clipboard contents are explicit.
Attacks that exploit this kind of access
Write text to the clipboard. Requires the. It is categorised as a Write tool in the Computer Use Windows MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Computer Use Windows MCP server in PolicyLayer and add a rule for write_clipboard: 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 Computer Use Windows. Nothing to install.
write_clipboard is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the write_clipboard 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 write_clipboard. 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.
write_clipboard is provided by the Computer Use Windows MCP server (wimi321/windows-computer-use-skill). 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 →