start_chisel_with_options
AI agents invoke start_chisel_with_options to trigger actions in Foundry MCP Project. 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.
Chisel is an interactive environment that executes code with effects on local or remote Ethereum networks (especially with anvil integration via 'start_anvil_with_options'). While not destructive by itself, it can execute arbitrary smart contract code, deploy contracts, and trigger state changes on development networks.
From the tool's definition Tool name 'start_chisel_with_options' indicates launching Chisel, an interactive Solidity REPL for Ethereum development.
Attacks that exploit this kind of access
start_chisel_with_options. It is categorised as a Execute tool in the Foundry MCP Project MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Foundry MCP Project MCP server in PolicyLayer and add a rule for start_chisel_with_options: 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 Project. Nothing to install.
start_chisel_with_options 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 start_chisel_with_options 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 start_chisel_with_options. 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.
start_chisel_with_options is provided by the Foundry MCP Project MCP server (lhemerly/foundry-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →