foundry_script · HashPilot MCP: Risk & Policy

WHAT IT DOES

What foundry_script does on HashPilot

AI agents invoke foundry_script 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_script needs a policy

This tool directly executes code (Solidity deployment scripts) whose effects depend on script arguments and content. While deployment itself is technically a write operation, the 'Run' verb and 'deployment script' nature indicate dynamic code execution that can trigger complex, multi-step operations on-chain.

From the tool's definition Tool name 'foundry_script' and description 'Run a Solidity deployment script' indicate execution of arbitrary code. Solidity scripts can deploy contracts, invoke state-changing functions, and interact with blockchain state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

foundry_script Rate-limited

foundry_script 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_script": {
      "limits": [
        {
          "counter": "foundry_script_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_script

What does the foundry_script tool do? +

Run a Solidity deployment script. Scripts provide more control than forge create for complex deployments with multiple contracts and configuration. 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_script? +

Register the HashPilot MCP server in PolicyLayer and add a rule for foundry_script: 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_script? +

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

Can I rate-limit foundry_script? +

Yes. Add a rate_limit block to the foundry_script 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_script completely? +

Set action: deny in the PolicyLayer policy for foundry_script. 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_script? +

foundry_script 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.