Navigate to a URL and return its full readable content + interactive elements in one call. Use this as the primary tool for
AI agents call pilot_get 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.
pilot_get performs navigation and content retrieval—core Read operations. While it controls a browser, the tool itself does not execute scripts, modify data, or perform destructive actions. The primary function is to fetch and return information. Navigation is necessary for retrieval and does not constitute an Execute risk in this context since the tool's purpose is data extraction, not arbitrary command execution.
From the tool's definition Tool description states 'Navigate to a URL and return its full readable content + interactive elements in one call.' This is a retrieval operation that fetches and returns page content without modifying, deleting, or executing arbitrary code on the target…
Documented attack patterns abuse exactly the kind of access pilot_get 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_get:
{
"version": "1",
"default": "deny",
"tools": {
"pilot_get": {}
}
}pilot_get 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.
Navigate to a URL and return its full readable content + interactive elements in one call. Use this as the primary tool for. 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_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 Pilot. Nothing to install.
pilot_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 pilot_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 pilot_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.
pilot_get 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.