AI agents use create-payee to create or update resources in Actual — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Actual environment.
This tool creates a new payee record within Actual Budget, which is a reversible operation (payees can be deleted via delete-payee). Creating payees is a normal data management operation that does not execute arbitrary code, delete data irreversibly, or process financial transactions. The blast radius if misused (e.g., creating many dummy payees) is contained to the budget database and easily remediated.
From the tool's definition Tool name 'create-payee' and description 'Create a new payee' explicitly indicate creation of new data without irreversible deletion or external financial movement.
Documented attack patterns abuse exactly the kind of access create-payee gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Actual, and nothing reaches the server without passing your rules. This is the rule we recommend for create-payee:
{
"version": "1",
"default": "deny",
"tools": {
"create-payee": {
"limits": [
{
"counter": "create-payee_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} create-payee 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 new payee. It is categorised as a Write tool in the Actual MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Actual MCP server in PolicyLayer and add a rule for create-payee: 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 Actual. Nothing to install.
create-payee 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 create-payee 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 create-payee. 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.
create-payee is provided by the Actual MCP server (s-stefanov/actual-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 25 Actual tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
25 Actual tools catalogued and risk-classified — across an index of 42,500+ MCP servers.