hardhat_test · HashPilot MCP: Risk & Policy

WHAT IT DOES

What hardhat_test does on HashPilot

AI agents invoke hardhat_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 hardhat_test needs a policy

This tool runs code (Mocha/Chai test suites) on a blockchain development environment. Executing arbitrary test scripts can trigger smart contract deployments, state changes, or interactions with live networks depending on configuration. The blast radius is high because misconfigured or malicious tests could deploy contracts, consume gas, or interact with real Hedera accounts.

From the tool's definition 'Run Mocha/Chai tests for smart contracts' — executes test code/scripts against smart contracts

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hardhat_test Rate-limited

hardhat_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": {
    "hardhat_test": {
      "limits": [
        {
          "counter": "hardhat_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 hardhat_test

What does the hardhat_test tool do? +

Run Mocha/Chai tests for smart contracts. Supports filtering by file or pattern. 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 hardhat_test? +

Register the HashPilot MCP server in PolicyLayer and add a rule for hardhat_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 hardhat_test? +

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

Can I rate-limit hardhat_test? +

Yes. Add a rate_limit block to the hardhat_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 hardhat_test completely? +

Set action: deny in the PolicyLayer policy for hardhat_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 hardhat_test? +

hardhat_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.