AI agents use hardhat_init to create or update resources in HashPilot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your HashPilot environment.
This tool creates files and directory structures on the local filesystem. It is a Write operation as it creates new artifacts (directories, config files, contracts, scripts) but does not delete existing data, execute code, or involve financial transactions. Misuse could create unwanted files or overwrite project configurations, giving it medium severity.
From the tool's definition Initialize a new Hardhat project...Creates directory structure, config files, sample contracts, tests, and deployment scripts.
Attacks that exploit this kind of access
Initialize a new Hardhat project with Hedera network configuration. Creates directory structure, config files, sample contracts, tests, and deployment scripts. It is categorised as a Write tool in the HashPilot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the HashPilot MCP server in PolicyLayer and add a rule for hardhat_init: 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.
hardhat_init is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the hardhat_init 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 hardhat_init. 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.
hardhat_init 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.
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 →