foundry_test · HashPilot MCP: Risk & Policy

WHAT IT DOES

What foundry_test does on HashPilot

AI agents invoke foundry_test 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_test needs a policy

This tool runs code (Forge/Foundry test suite written in Solidity) against a blockchain environment, potentially including fork mode which interacts with live networks. Arbitrary test execution with fuzzing can trigger unintended contract calls, state changes, or resource exhaustion. The blast radius is high because tests may execute real transactions on forked or live networks.

From the tool's definition 'Run Forge test suite' and 'native fuzzing support' — executes Solidity smart contract tests, potentially with 'forking' (forking a live blockchain state) and arbitrary test code execution

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

foundry_test Rate-limited

foundry_test 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_test": {
      "limits": [
        {
          "counter": "foundry_test_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_test

What does the foundry_test tool do? +

Run Forge test suite with native fuzzing support. Tests are written in Solidity. Supports filtering, gas reports, and forking. 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_test? +

Register the HashPilot MCP server in PolicyLayer and add a rule for foundry_test: 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_test? +

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

Can I rate-limit foundry_test? +

Yes. Add a rate_limit block to the foundry_test 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_test completely? +

Set action: deny in the PolicyLayer policy for foundry_test. 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_test? +

foundry_test 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.