AI agents call get_clipboard to retrieve information from MacWright without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves clipboard data without side effects. While clipboard contents could theoretically contain sensitive information (lowering confidence slightly from 1.0), the action itself is purely informational and non-destructive. It falls squarely under the 'Read' category as it queries system state without altering it.
From the tool's definition Tool name and description clearly indicate a read-only operation: 'Read the current contents of the system clipboard'. No modification, deletion, execution, or financial transaction occurs.
Attacks that exploit this kind of access
Read the current contents of the system clipboard. Supports plain text (default) and HTML formats. It is categorised as a Read tool in the MacWright MCP Server, which means it retrieves data without modifying state.
Register the MacWright MCP server in PolicyLayer and add a rule for get_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 MacWright. Nothing to install.
get_clipboard 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 get_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 get_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.
get_clipboard is provided by the MacWright MCP server (ruchit-p/macwright). 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 →