Block network requests matching URL patterns to speed up page loads and reduce token noise from ad/tracker content. Use when the user wants to block ads, trackers, analytics scripts, or any noisy domain. Blocked requests are aborted before they hit the network — faster loads, smaller snapshots. U...
AI agents invoke pilot_block to trigger actions in Pilot. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool configures the browser to intercept and abort network requests matching URL patterns. While it doesn't delete data or move money, it actively executes a browser-level operation (network request blocking) that affects ongoing and future page loads. It goes beyond a simple read or write — it installs a persistent filter that alters the browser's network behavior, classifying it as Execute.
From the tool's definition 'Blocked requests are aborted before they hit the network' — this triggers an active network interception and abort operation via Playwright, modifying browser behavior for subsequent requests
Documented attack patterns abuse exactly the kind of access pilot_block 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_block:
{
"version": "1",
"default": "deny",
"tools": {
"pilot_block": {
"limits": [
{
"counter": "pilot_block_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}pilot_block stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Block network requests matching URL patterns to speed up page loads and reduce token noise from ad/tracker content. Use when the user wants to block ads, trackers, analytics scripts, or any noisy domain. Blocked requests are aborted before they hit the network — faster loads, smaller snapshots. Use the built-in. It is categorised as a Execute tool in the Pilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pilot MCP server in PolicyLayer and add a rule for pilot_block: 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_block is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the pilot_block 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_block. 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_block 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.