Create a Check that can be cashed by the destination account
AI agents use check-create to create or update resources in Xrpl mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xrpl mcp environment.
This tool creates a Check object on the XRP Ledger, which is a reversible financial instrument (it can be cancelled before being cashed). It writes a new ledger object but does not immediately move funds, distinguishing it from a direct payment.
From the tool's definition Create a Check that can be cashed by the destination account
Documented attack patterns abuse exactly the kind of access check-create 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 check-create:
{
"version": "1",
"default": "deny",
"tools": {
"check-create": {
"limits": [
{
"counter": "check-create_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}check-create stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a Check that can be cashed by the destination account. It is categorised as a Write tool in the Xrpl mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xrpl MCP server in PolicyLayer and add a rule for check-create: 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.
check-create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the check-create 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 check-create. 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.
check-create 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.