AI agents use update_category to create or update resources in Monarch — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Monarch environment.
This tool modifies existing category data reversibly (Write category). It operates on financial transaction metadata rather than moving money directly, so it does not qualify as Financial.
From the tool's definition Tool name 'update_category' indicates modification of transaction categories in a financial application (Monarch Money). Sibling context shows this is a financial management system with transaction categorization features.
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 Monarch, 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_category. It is categorised as a Write tool in the Monarch MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Monarch 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 Monarch. 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 Monarch MCP server (robcerda/monarch-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 50 Monarch tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
50 Monarch tools catalogued and risk-classified — across an index of 42,500+ MCP servers.