AI agents call foundry_inspect to retrieve information from HashPilot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
foundry_inspect performs queries on compiled contract artifacts to return information (ABI, bytecode, storage layout, assembly). This is a data retrieval operation with no side effects, no code execution, no state modification, and no irreversible actions. The highest risk would be information disclosure if sensitive contract details were exposed, but retrieval itself is characteristic of the Read category.
From the tool's definition Tool description states 'Inspect compiled contract artifacts' and 'Can retrieve ABI, bytecode, storage layout, assembly' — all read-only inspection operations that retrieve data without modification or execution.
Attacks that exploit this kind of access
Inspect compiled contract artifacts. Can retrieve ABI, bytecode, storage layout, assembly, and more. It is categorised as a Read tool in the HashPilot MCP Server, which means it retrieves data without modifying state.
Register the HashPilot MCP server in PolicyLayer and add a rule for foundry_inspect: 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.
foundry_inspect is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the foundry_inspect 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 foundry_inspect. 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.
foundry_inspect 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 →