AI agents invoke anvil_stop to trigger actions in Foundry MCP Server. 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.
This tool triggers termination of an external service (Anvil node), which is a process control operation. While not destructive in the sense of permanent data loss, it has irreversible immediate effects on system state and could interrupt ongoing operations or tests. It exceeds Write (which is reversible) and fits Execute (runs/triggers external operations).
From the tool's definition Tool description states 'Stop a running Anvil instance'. Anvil is a local Ethereum node used for testing and development. Stopping it terminates a running process, which is an execute action with external effects on system state.
Documented attack patterns abuse exactly the kind of access anvil_stop gives an agent:
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_stop:
{
"version": "1",
"default": "deny",
"tools": {
"anvil_stop": {
"limits": [
{
"counter": "anvil_stop_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}anvil_stop 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.
Free to start. No card required.
Stop a running Anvil instance. 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.
Register the Foundry MCP Server MCP server in PolicyLayer and add a rule for anvil_stop: 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.
anvil_stop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the anvil_stop 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.
Set action: deny in the PolicyLayer policy for anvil_stop. 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.
anvil_stop 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.
Deterministic rules across all 16 Foundry MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
16 Foundry MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.