Find an element by visible text, label, placeholder, or role — without running a full snapshot. Use when you know what you want to click or fill but don
AI agents call pilot_find 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 locates/queries a DOM element based on descriptive attributes. It retrieves a reference to an element without interacting with it or causing side effects. It is a read/lookup operation analogous to a search or get.
From the tool's definition Find an element by visible text, label, placeholder, or role — without running a full snapshot
Documented attack patterns abuse exactly the kind of access pilot_find 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_find:
{
"version": "1",
"default": "deny",
"tools": {
"pilot_find": {}
}
}pilot_find 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.
Find an element by visible text, label, placeholder, or role — without running a full snapshot. Use when you know what you want to click or fill but don. 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_find: 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_find 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_find 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_find. 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_find 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.