Assert a condition about the current page state and fail with a structured error if the assertion is not met. Use when the user wants to verify the outcome of an action — that a URL was reached, text is present or absent, an element is visible/hidden/enabled, or an input has a specific value. Ret...
AI agents call pilot_assert 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 reads/inspects the current page state (URL, visible text, element properties) and returns a pass/fail result. It does not modify, execute, or delete anything — it is purely a verification/observation operation.
From the tool's definition Assert a condition about the current page state and fail with a structured error if the assertion is not met
Documented attack patterns abuse exactly the kind of access pilot_assert 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_assert:
{
"version": "1",
"default": "deny",
"tools": {
"pilot_assert": {}
}
}pilot_assert 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.
Assert a condition about the current page state and fail with a structured error if the assertion is not met. Use when the user wants to verify the outcome of an action — that a URL was reached, text is present or absent, an element is visible/hidden/enabled, or an input has a specific value. Returns a clear pass/fail signal for agent-driven test flows. Parameters: - url: Assert the current page URL equals or contains this string - text_present: Assert this text is visible somewhere on the page (waits up to 5s) - text_absent: Assert this text is NOT visible on the page - ref: Element ref (@eN) to assert a state or value on - state: Expected element state —. 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_assert: 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_assert 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_assert 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_assert. 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_assert 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.