token_manage · HashPilot MCP: Risk & Policy

WHAT IT DOES

What token_manage does on HashPilot

AI agents invoke token_manage 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 token_manage needs a policy

This tool triggers real blockchain operations with irreversible or financially significant effects: token transfers move assets between accounts (Financial), burning destroys tokens permanently (Destructive), and minting/freezing/creating alter on-chain state (Execute/Write).

From the tool's definition Execute ANY token operation through a single unified interface — including create, associate, transfer, mint, burn, freeze/unfreeze on the Hedera blockchain

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

token_manage Rate-limited

token_manage 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": {
    "token_manage": {
      "limits": [
        {
          "counter": "token_manage_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 token_manage

What does the token_manage tool do? +

Comprehensive Hedera Token Service (HTS) management. Execute ANY token operation through a single unified interface. OPERATIONS: - create: Create new fungible token with custom fees, keys, and supply controls - associate: Associate token with account (required before receiving tokens) - transfer: Transfer tokens between accounts - mint: Mint additional tokens (requires supply key) - burn: Burn tokens from treasury - freeze/unfreeze: Control account. 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 token_manage? +

Register the HashPilot MCP server in PolicyLayer and add a rule for token_manage: 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 token_manage? +

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

Can I rate-limit token_manage? +

Yes. Add a rate_limit block to the token_manage 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 token_manage completely? +

Set action: deny in the PolicyLayer policy for token_manage. 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 token_manage? +

token_manage 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.