Copy text to clipboard or retrieve current clipboard content. Use
AI agents call Clipboard-Tool to retrieve information from Windows-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Copying to clipboard or reading clipboard content are non-destructive operations with minimal side effects. Even if an agent copies sensitive data to clipboard, the action is reversible (clipboard can be cleared) and does not modify persistent system state. The primary risk is information disclosure of clipboard contents, which is a read-level concern.
From the tool's definition Tool description states it can 'Copy text to clipboard or retrieve current clipboard content.' Both operations are data retrieval or temporary data placement with no destructive or irreversible effects.
Attacks that exploit this kind of access
Copy text to clipboard or retrieve current clipboard content. Use. It is categorised as a Read tool in the Windows-MCP MCP Server, which means it retrieves data without modifying state.
Register the Windows- MCP server in PolicyLayer and add a rule for Clipboard-Tool: 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-MCP. Nothing to install.
Clipboard-Tool is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the Clipboard-Tool 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 Clipboard-Tool. 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.
Clipboard-Tool is provided by the Windows- MCP server (stepbystep-1/winows-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 →