Read the current clipboard text.
AI agents call clipboard_get to retrieve information from Hermes Computer Use without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves clipboard content without modifying, deleting, or executing anything. It has a minimal blast radius—the data exposed is limited to what is already in the user's clipboard. While clipboard content could theoretically be sensitive, the tool itself performs only a passive read operation with no irreversible effects or capability to trigger external actions.
From the tool's definition Tool name 'clipboard_get' and description 'Read the current clipboard text' explicitly indicate a read-only operation with no side effects.
Attacks that exploit this kind of access
Read the current clipboard text. It is categorised as a Read tool in the Hermes Computer Use MCP Server, which means it retrieves data without modifying state.
Register the Hermes Computer Use MCP server in PolicyLayer and add a rule for clipboard_get: 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 Hermes Computer Use. Nothing to install.
clipboard_get 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_get 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_get. 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_get is provided by the Hermes Computer Use MCP server (noah3521/hermes-computer-use). 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 →