mirror_call_contract · HashPilot MCP: Risk & Policy

WHAT IT DOES

What mirror_call_contract does on HashPilot

AI agents invoke mirror_call_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 mirror_call_contract needs a policy

Although the tool is described as 'read-only' with no state-changing effects, the act of executing EVM function calls—even view/pure functions—constitutes code execution. This falls under Execute category because it triggers external operations (smart contract function invocation) whose effects depend on the arguments supplied (which contract, which function, which parameters).

From the tool's definition Tool description states 'Execute EVM call simulation' and 'Call view/pure functions'. The verb 'Execute' and the capability to invoke smart contract functions classifies this as Execute rather than Read, despite being read-only and free.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mirror_call_contract Rate-limited

mirror_call_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": {
    "mirror_call_contract": {
      "limits": [
        {
          "counter": "mirror_call_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 mirror_call_contract

What does the mirror_call_contract tool do? +

Execute EVM call simulation (read-only, free). Call view/pure functions without gas cost. 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 mirror_call_contract? +

Register the HashPilot MCP server in PolicyLayer and add a rule for mirror_call_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 mirror_call_contract? +

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

Can I rate-limit mirror_call_contract? +

Yes. Add a rate_limit block to the mirror_call_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 mirror_call_contract completely? +

Set action: deny in the PolicyLayer policy for mirror_call_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 mirror_call_contract? +

mirror_call_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.