Compose a transaction to permanently destroy (burn) Counterparty tokens
AI agents call compose_destroy to permanently remove resources in 21e14 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
tag | string | — | Optional tag/memo for the destruction |
asset | string | Yes | Asset to destroy |
address | string | Yes | Source Bitcoin address |
quantity | integer | Yes | Raw integer amount to destroy. For divisible: human amount * 10^8. |
inputs_set | string | — | Comma-separated UTXOs to use as inputs (txid:vout) |
sat_per_vbyte | number | — | Fee rate in satoshis per virtual byte (e.g. 1, 5.5, 0.15). Check get_fee_estimate for current market rates. |
Parameters from the server's own tool schema.
This tool composes transactions that permanently burn tokens, which cannot be undone. While the actual token destruction occurs upon broadcast (not within this tool), the compose function creates irrevocable instructions. The blast radius is high: an agent error could burn valuable tokens belonging to the user.
From the tool's definition Tool name 'compose_destroy' and description 'permanently destroy (burn) Counterparty tokens' explicitly indicate irreversible deletion of digital assets.
Documented attack patterns abuse exactly the kind of access compose_destroy gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 21e14, and nothing reaches the server without passing your rules. This is the rule we recommend for compose_destroy:
{
"version": "1",
"default": "deny",
"hide": [
"compose_destroy"
]
} compose_destroy disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Compose a transaction to permanently destroy (burn) Counterparty tokens. It is categorised as a Destructive tool in the 21e14 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
compose_destroy accepts 6 parameters: tag, asset, address, quantity, inputs_set, sat_per_vbyte. Required: asset, address, quantity. The full parameter table on this page comes from the server's own tool schema.
Register the 21e14 MCP server in PolicyLayer and add a rule for compose_destroy: 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 21e14. Nothing to install.
compose_destroy is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the compose_destroy 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 compose_destroy. 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.
compose_destroy is provided by the 21e14 MCP server (@21e14/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 21e14, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
48 21e14 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.