hardhat_execute_contract · HashPilot MCP: Risk & Policy

WHAT IT DOES

What hardhat_execute_contract does on HashPilot

AI agents invoke hardhat_execute_contract 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_execute_contract needs a policy

This tool executes arbitrary contract functions on the Hedera blockchain with financial and state implications. While 'Execute' is the primary category, the tool commits blockchain transactions that cost gas and alter contract state irreversibly.

From the tool's definition Tool description explicitly states 'Execute state-changing contract function' and 'sends transaction' on blockchain. The word 'Execute' combined with state-changing operations and gas requirements indicates code execution with external effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hardhat_execute_contract Rate-limited

hardhat_execute_contract 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_execute_contract": {
      "limits": [
        {
          "counter": "hardhat_execute_contract_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_execute_contract

What does the hardhat_execute_contract tool do? +

Execute state-changing contract function. Requires gas and sends transaction. 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_execute_contract? +

Register the HashPilot MCP server in PolicyLayer and add a rule for hardhat_execute_contract: 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_execute_contract? +

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

Can I rate-limit hardhat_execute_contract? +

Yes. Add a rate_limit block to the hardhat_execute_contract 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_execute_contract completely? +

Set action: deny in the PolicyLayer policy for hardhat_execute_contract. 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_execute_contract? +

hardhat_execute_contract 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.