Take a PNG screenshot with red overlay boxes and ref labels at each @eN/@cN element position. Use when the user wants a visual debug overlay showing where each snapshot ref is located on the page, or needs to verify element positions visually. Requires a prior pilot_snapshot call to populate the ...
AI agents call pilot_annotated_screenshot to retrieve information from Pilot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only captures and returns visual information about the current state of the browser. It does not modify data, execute arbitrary code, delete anything, or commit financial transactions. The optional output_path parameter allows saving to disk but does not delete or overwrite existing files by default. The tool's purpose is diagnostic/observational, making it a Read operation with minimal risk.
From the tool's definition Tool takes a screenshot with visual overlays and returns a PNG image and file path. The description states it is for 'visual debug overlay' and 'visual capture' - it retrieves and displays visual information about the current browser state without modifying…
Documented attack patterns abuse exactly the kind of access pilot_annotated_screenshot gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pilot, and nothing reaches the server without passing your rules. This is the rule we recommend for pilot_annotated_screenshot:
{
"version": "1",
"default": "deny",
"tools": {
"pilot_annotated_screenshot": {}
}
}pilot_annotated_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 a PNG screenshot with red overlay boxes and ref labels at each @eN/@cN element position. Use when the user wants a visual debug overlay showing where each snapshot ref is located on the page, or needs to verify element positions visually. Requires a prior pilot_snapshot call to populate the ref positions. For a clean visual capture without debug overlays, use pilot_screenshot instead. Parameters: - output_path: Optional file path to save the annotated screenshot (default: temp directory) Returns: The annotated screenshot as a base64 PNG image and the file path where it was saved. Errors: -. It is categorised as a Read tool in the Pilot MCP Server, which means it retrieves data without modifying state.
Register the Pilot MCP server in PolicyLayer and add a rule for pilot_annotated_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 Pilot. Nothing to install.
pilot_annotated_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 pilot_annotated_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 pilot_annotated_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.
pilot_annotated_screenshot is provided by the Pilot MCP server (tacosyhorchata/pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 61 Pilot tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
61 Pilot tools catalogued and risk-classified — across an index of 42,500+ MCP servers.