AI agents use update-rule 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 modifies existing financial rules but does not delete or create new ones, and does not move money directly. The update is reversible—rules can be modified again or reverted. While it affects financial behavior (rules may trigger or affect transactions), the direct action is data modification, not financial movement or irreversible deletion.
From the tool's definition Tool name is 'update-rule' with description 'Update a rule'. The verb 'update' indicates modification of existing data (a rule in the Actual Budget system) in a reversible manner.
Documented attack patterns abuse exactly the kind of access update-rule 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 update-rule:
{
"version": "1",
"default": "deny",
"tools": {
"update-rule": {
"limits": [
{
"counter": "update-rule_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-rule 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.
Update a rule. 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 update-rule: 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.
update-rule 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 update-rule 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 update-rule. 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.
update-rule 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.