hcs_message · HashPilot MCP: Risk & Policy

WHAT IT DOES

What hcs_message does on HashPilot

AI agents invoke hcs_message to trigger actions in HashPilot. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why hcs_message needs a policy

The 'submit' operation posts messages to the Hedera blockchain, which is an irreversible external action with real consensus-layer side effects (transaction fees, permanent on-chain record). The 'query' operation is read-only, but per the rules the most severe applicable category applies.

From the tool's definition 'submit: Submit message to topic (auto-chunks if >1KB)' — triggers an external blockchain operation that publishes data to Hedera Consensus Service, causing on-chain side effects

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hcs_message Rate-limited

hcs_message stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "hcs_message": {
      "limits": [
        {
          "counter": "hcs_message_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches HashPilot, so you can run agents against it safely.

FAQ

Questions about hcs_message

What does the hcs_message tool do? +

Hedera Consensus Service (HCS) message operations. OPERATIONS: - submit: Submit message to topic (auto-chunks if >1KB) - query: Query historical messages with filtering (FREE via Mirror Node) USE THIS FOR: Publishing messages, retrieving consensus-ordered data, auditable logs. It is categorised as a Execute tool in the HashPilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on hcs_message? +

Register the HashPilot MCP server in PolicyLayer and add a rule for hcs_message: 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.

What risk level is hcs_message? +

hcs_message is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit hcs_message? +

Yes. Add a rate_limit block to the hcs_message 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.

How do I block hcs_message completely? +

Set action: deny in the PolicyLayer policy for hcs_message. 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.

What MCP server provides hcs_message? +

hcs_message 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.