AI agents call message_query 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 tool retrieves historical data from a blockchain topic without side effects. Querying public blockchain data poses minimal risk; the worst misuse would be information disclosure of already-public messages. The free public Mirror Node API further indicates this is read-only access to non-sensitive historical records.
From the tool's definition Tool name 'message_query' and description 'Query historical messages' indicate a retrieval operation. The description explicitly states it queries messages from a topic via Mirror Node REST API without modification capabilities—it only 'Returns messages with…
Attacks that exploit this kind of access
Query historical messages from an HCS topic via Mirror Node REST API (FREE). Messages are base64 decoded automatically. Returns messages with timestamps and sequence numbers. 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 message_query: 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.
message_query 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 message_query 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 message_query. 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.
message_query 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 →