Claw back tokens issued by your account from a holder
AI agents use token-clawback to commit financial operations through Xrpl mcp — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool forcibly removes tokens from another account's holdings and returns them to the issuer. This is an irreversible financial action that directly affects the token balances of other parties on the XRP Ledger, making it both Financial and Destructive in nature. Financial is the most severe applicable category.
From the tool's definition Claw back tokens issued by your account from a holder
Documented attack patterns abuse exactly the kind of access token-clawback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Xrpl mcp, and nothing reaches the server without passing your rules. This is the rule we recommend for token-clawback:
{
"version": "1",
"default": "deny",
"tools": {
"token-clawback": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
} Any call to token-clawback is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Claw back tokens issued by your account from a holder. It is categorised as a Financial tool in the Xrpl mcp MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Xrpl MCP server in PolicyLayer and add a rule for token-clawback: 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 Xrpl mcp. Nothing to install.
token-clawback is a Financial 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 token-clawback 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 token-clawback. 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.
token-clawback is provided by the Xrpl MCP server (romthpt/mcp-xrpl). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Xrpl mcp, 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.
71 Xrpl mcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.