Take visual screenshot in base64 PNG. Use ONLY for visual verification (CSS, layout, proof). Prefer snapshot for most tasks — much more token-efficient.
AI agents call screenshot to retrieve information from Camofox 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 a visual representation of a webpage state. It has no side effects, does not execute code or commands, does not modify data, and does not trigger financial or destructive actions. It is purely observational/read-only. The high confidence reflects the clear informational nature of the tool and explicit documentation limiting its use to verification purposes.
From the tool's definition Tool name 'screenshot' and description explicitly states 'Take visual screenshot in base64 PNG' with guidance to use 'ONLY for visual verification (CSS, layout, proof)'. The tool retrieves visual data without modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access screenshot gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Camofox, and nothing reaches the server without passing your rules. This is the rule we recommend for screenshot:
{
"version": "1",
"default": "deny",
"tools": {
"screenshot": {}
}
} screenshot is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Take visual screenshot in base64 PNG. Use ONLY for visual verification (CSS, layout, proof). Prefer snapshot for most tasks — much more token-efficient. It is categorised as a Read tool in the Camofox MCP Server, which means it retrieves data without modifying state.
Register the Camofox 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 Camofox. 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 Camofox MCP server (redf0x1/camofox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 47 Camofox tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
47 Camofox tools catalogued and risk-classified — across an index of 42,500+ MCP servers.