Query an HCS topic with a natural language question. Returns AI-ranked relevant
AI agents call hcs_query to retrieve information from Hedera Toolbox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns data from blockchain consensus records. While it operates on production Hedera infrastructure and has financial implications (metered access paid in HBAR micropayments), the core action is read-only retrieval.
From the tool's definition Tool name 'hcs_query' and description 'Query an HCS topic with a natural language question. Returns AI-ranked relevant...' indicates data retrieval with no data modification.
Attacks that exploit this kind of access
Query an HCS topic with a natural language question. Returns AI-ranked relevant. It is categorised as a Read tool in the Hedera Toolbox MCP Server, which means it retrieves data without modifying state.
Register the Hedera Toolbox MCP server in PolicyLayer and add a rule for hcs_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 Hedera Toolbox. Nothing to install.
hcs_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 hcs_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 hcs_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.
hcs_query is provided by the Hedera Toolbox MCP server (mountainmystic/hederatoolbox). 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 →