burn_tokens

THE RISK

Critical Risk

Why burn_tokens needs a policy

Burning tokens is an irreversible destruction of financial assets. Once tokens are burned, they cannot be recovered. Given this is a stablecoin payment system, burning tokens has direct financial consequences and constitutes a destructive, unrecoverable action. The financial context elevates severity to critical.

From the tool's definition 'Burn TIP-20 tokens from the caller' — burning tokens irreversibly destroys them from circulation; this action cannot be undone

Documented attack patterns abuse exactly the kind of access burn_tokens gives an agent:

POLICY

How to control burn_tokens

PolicyLayer is an MCP gateway — it sits between your AI agents and Tempo, and nothing reaches the server without passing your rules. This is the rule we recommend for burn_tokens:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "burn_tokens"
  ]
}

burn_tokens disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register Tempo — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Tempo tools

Financial cancel_order Cancel an open order on the DEX. The remaining unfilled amount will be Financial cancel_scheduled_payment Cancel a pending scheduled payment before it executes. Financial swap_stablecoins Execute a stablecoin swap on Tempo DEX. Financial claim_rewards Claim all pending rewards for a TIP-20 token. Rewards are sent to your wallet Financial distribute_rewards Distribute rewards to all opted-in holders of a TIP-20 token. Financial mint_tokens Mint new TIP-20 tokens to a recipient address. Financial opt_in_rewards Opt into rewards for a TIP-20 token. After opting in, you will earn rewards Financial opt_out_rewards Opt out of rewards for a TIP-20 token. By default, any pending rewards will be

All 61 Tempo tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Govern database agents → Read-only defaults, blocked table drops, and no DELETE without a WHERE clause on every query.
Critical-risk tools in Tempo → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →
PolicyLayer vs alternatives → How deterministic, per-call MCP policy compares with gateways, identity layers, and authorisation platforms.

FAQ

Questions about burn_tokens

What does the burn_tokens tool do? +

Burn TIP-20 tokens from the caller. It is categorised as a Destructive tool in the Tempo MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on burn_tokens? +

Register the Tempo MCP server in PolicyLayer and add a rule for burn_tokens: 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 Tempo. Nothing to install.

What risk level is burn_tokens? +

burn_tokens is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit burn_tokens? +

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

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

burn_tokens is provided by the Tempo MCP server (arome3/tempo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Tempo tool call.

Start from Tempo, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →