Run the Valdez Tanker (VALD) demo — Koelling-Remy 1983 Alaska Pipeline model, the paradigm-integration motivator. Crude flows continuously into the Valdez Marine Terminal storage tank (Flow); tankers arrive discretely to drain it (Item); DRS handles both via F2I / I2F transitions. Returns engine ...
Part of the DiscreteRate server.
Free to start. No card required.
AI agents invoke run_valdez_tanker to trigger processes or run actions in DiscreteRate. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
run_valdez_tanker can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"run_valdez_tanker": {
"limits": [
{
"counter": "run_valdez_tanker_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full DiscreteRate policy for all 13 tools.
These attack patterns abuse exactly the kind of access run_valdez_tanker gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Run the Valdez Tanker (VALD) demo — Koelling-Remy 1983 Alaska Pipeline model, the paradigm-integration motivator. Crude flows continuously into the Valdez Marine Terminal storage tank (Flow); tankers arrive discretely to drain it (Item); DRS handles both via F2I / I2F transitions. Returns engine output including tanker arrival/departure events and tank-level trace. ANTI-FABRICATION: numbers come from a real engine run; quote verbatim.. It is categorised as a Execute tool in the DiscreteRate MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DiscreteRate MCP server in PolicyLayer and add a rule for run_valdez_tanker: 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 DiscreteRate. Nothing to install.
run_valdez_tanker 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 run_valdez_tanker 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 run_valdez_tanker. 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.
run_valdez_tanker is provided by the DiscreteRate MCP server (https://discreterate.com/mcp/v1). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 DiscreteRate tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.