Write text to the clipboard
AI agents use desktop_clipboard_write to create or update resources in MCP Desktop Tools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Desktop Tools environment.
This tool creates or modifies clipboard data reversibly. While clipboard writes are generally low-impact, they can facilitate prompt injection attacks, credential theft preparation, or manipulation of data that the user later pastes into sensitive applications.
From the tool's definition Tool name 'desktop_clipboard_write' and description 'Write text to the clipboard' explicitly indicate modification of system clipboard data.
Attacks that exploit this kind of access
Write text to the clipboard. It is categorised as a Write tool in the MCP Desktop Tools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Desktop Tools MCP server in PolicyLayer and add a rule for desktop_clipboard_write: 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 MCP Desktop Tools. Nothing to install.
desktop_clipboard_write 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 desktop_clipboard_write 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 desktop_clipboard_write. 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.
desktop_clipboard_write is provided by the MCP Desktop Tools MCP server (k1ta141k/mcp-desktop-tools). 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 →