AI agents call network_info 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.
This is a pure query/retrieval operation that returns read-only network information. It has no capability to modify state, execute transactions, or cause irreversible changes. The blast radius of misuse is minimal—an agent could only access publicly available network endpoint information. This clearly fits the Read category with low severity.
From the tool's definition Tool retrieves and returns network configuration data (network name, Mirror Node URL, JSON-RPC Relay endpoint) with no modification or side effects.
Attacks that exploit this kind of access
Get current Hedera network configuration. RETURNS: Network name, Mirror Node URL, JSON-RPC Relay endpoint USE FOR: Verifying active network, getting endpoint URLs, network status. 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 network_info: 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.
network_info 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 network_info 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 network_info. 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.
network_info 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 →