AI agents use update-category 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 or modifies data in a reversible manner (Write category), fitting the Write classification. It does not delete data (would be Destructive), execute arbitrary code (would be Execute), or move money (would be Financial). Severity is medium because incorrect updates to budget categories could corrupt financial records and mislead budget tracking, but the change is reversible via subsequent updates.
From the tool's definition Tool name 'update-category' and description 'Update a category' indicate modification of existing data. The sibling tools include both 'create-category' (Write) and 'delete-category' (Destructive), establishing this server's domain as budget/financial…
Documented attack patterns abuse exactly the kind of access update-category 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-category:
{
"version": "1",
"default": "deny",
"tools": {
"update-category": {
"limits": [
{
"counter": "update-category_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-category 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 category. 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-category: 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-category 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-category 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-category. 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-category 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.