foundry_anvil_start · HashPilot MCP: Risk & Policy

WHAT IT DOES

What foundry_anvil_start does on HashPilot

AI agents invoke foundry_anvil_start to trigger actions in HashPilot. 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.

WHY IT NEEDS A POLICY

Why foundry_anvil_start needs a policy

This tool triggers execution of an external blockchain simulator/node (Anvil), which is a computational operation that can have significant effects on the local environment and subsequent behavior. While not destructive in the traditional sense (the node can be stopped), it executes commands that set up complex infrastructure.

From the tool's definition Tool name includes 'start' and description states 'Start Anvil local Ethereum node' and 'Can fork from Hedera testnet/mainnet'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

foundry_anvil_start Rate-limited

foundry_anvil_start 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "foundry_anvil_start": {
      "limits": [
        {
          "counter": "foundry_anvil_start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches HashPilot, so you can run agents against it safely.

FAQ

Questions about foundry_anvil_start

What does the foundry_anvil_start tool do? +

Start Anvil local Ethereum node for testing. Can fork from Hedera testnet/mainnet for realistic testing environment. It is categorised as a Execute tool in the HashPilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on foundry_anvil_start? +

Register the HashPilot MCP server in PolicyLayer and add a rule for foundry_anvil_start: 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 HashPilot. Nothing to install.

What risk level is foundry_anvil_start? +

foundry_anvil_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit foundry_anvil_start? +

Yes. Add a rate_limit block to the foundry_anvil_start 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.

How do I block foundry_anvil_start completely? +

Set action: deny in the PolicyLayer policy for foundry_anvil_start. 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.

What MCP server provides foundry_anvil_start? +

foundry_anvil_start is provided by the HashPilot MCP server (justmert/hashpilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.