anvil_start

THE RISK

High Risk

Starting an Anvil instance is an Execute action because it launches and runs an external operation (an Ethereum node) whose effects are not immediately reversible without stopping the process. While it doesn't directly modify blockchain state, it sets up an execution environment for blockchain operations.

From the tool's definition Tool starts a new Anvil instance (local Ethereum node) - this initiates a process with external system effects that depend on arguments and configuration.

Documented attack patterns abuse exactly the kind of access anvil_start gives an agent:

HOW TO CONTROL ANVIL_START

PolicyLayer is an MCP gateway — it sits between your AI agents and Foundry MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for anvil_start:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "anvil_start": {
      "limits": [
        {
          "counter": "anvil_start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

anvil_start 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.

Create a free account and register Foundry MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

More Foundry MCP Server tools

Execute anvil_stop Stop a running Anvil instance Execute forge_script Run a Forge script from the workspace Execute cast_send Send a transaction to a contract function Write create_solidity_file Create or update a Solidity file in the workspace Read heimdall_decompile Decompile EVM bytecode to Solidity source code and ABI using Heimdall Read anvil_status Check if Anvil is running and get its status Read cast_balance Check the ETH balance of an address Read cast_call Call a contract function (read-only)

All 16 Foundry MCP Server tools →

Execute tools on other servers

Frida Game Hacking MCP remove_breakpoint Procmon request_elevation WireMCP capture_packets Pentest Ai run_probe

Go deeper

High-risk tools in Foundry MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the anvil_start tool do? +

Start a new Anvil instance (local Ethereum node). It is categorised as a Execute tool in the Foundry MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on anvil_start? +

Register the Foundry MCP Server MCP server in PolicyLayer and add a rule for anvil_start: 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 Foundry MCP Server. Nothing to install.

What risk level is anvil_start? +

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

Can I rate-limit anvil_start? +

Yes. Add a rate_limit block to the anvil_start 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 anvil_start completely? +

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

anvil_start is provided by the Foundry MCP Server MCP server (praneshasp/foundry-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Foundry MCP Server tool call.

Deterministic rules across all 16 Foundry MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN FOUNDRY →

Free to start. No card required.

16 Foundry MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT ANVIL_START ON FOUNDRY MCP SERVER DOES

// THE RISK

// HOW TO CONTROL ANVIL_START

// EXPLORE