Intercept network requests matching a URL pattern and respond with custom status, headers, and body. Use when the user wants to mock API responses, simulate error states (401, 500), test loading states, or run frontend tests without a real backend. All requests matching the pattern are fulfilled ...
AI agents invoke pilot_intercept 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 executes code-like operations by intercepting and manipulating network traffic, causing the browser to execute different code paths based on attacker-controlled responses. While it doesn't directly execute shell commands, it executes frontend code with artificial inputs.
From the tool's definition Tool intercepts network requests and responds with custom status, headers, and body. Enables mocking API responses, simulating error states, and running tests—operations that modify browser behavior and trigger code execution paths based on injected responses.
Documented attack patterns abuse exactly the kind of access pilot_intercept 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_intercept:
{
"version": "1",
"default": "deny",
"tools": {
"pilot_intercept": {
"limits": [
{
"counter": "pilot_intercept_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}pilot_intercept 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.
Intercept network requests matching a URL pattern and respond with custom status, headers, and body. Use when the user wants to mock API responses, simulate error states (401, 500), test loading states, or run frontend tests without a real backend. All requests matching the pattern are fulfilled with the given response until cleared. Parameters: - pattern: URL glob pattern to intercept (e.g.,. 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_intercept: 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_intercept 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_intercept 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_intercept. 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_intercept 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.