Capture the current Xvfb screen and return it as a PNG image.
AI agents call screenshot 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 captures and returns screen content without modifying, executing code, deleting data, or triggering external operations. It is a pure read operation that retrieves the current state of the browser display. While the server overall enables browser automation with potential for misuse, this specific tool is read-only.
From the tool's definition Tool name 'screenshot' and description 'Capture the current Xvfb screen and return it as a PNG image' indicates retrieval of visual data with no side effects.
Attacks that exploit this kind of access
Capture the current Xvfb screen and return it as a PNG image. 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 screenshot: 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.
screenshot 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 screenshot 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 screenshot. 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.
screenshot 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 →