AI agents call mirror_search_logs 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.
The tool performs searches and filtering on existing blockchain logs/events. It has no capability to create, modify, delete, or execute transactions. The mirror_search_logs function is a passive data retrieval operation on immutable ledger records, characteristic of Read category tools. Blast radius is minimal: misuse would only expose publicly available blockchain event data.
From the tool's definition 'Search contract event logs globally by topic. Filter by event signature (topic0) or indexed parameters.' — this is a read-only query operation that retrieves blockchain event data without modifying state or executing transactions.
Attacks that exploit this kind of access
Search contract event logs globally by topic. Filter by event signature (topic0) or indexed parameters. 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 mirror_search_logs: 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.
mirror_search_logs 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 mirror_search_logs 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 mirror_search_logs. 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.
mirror_search_logs 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 →