Mark a transaction as reviewed (clears the needs_review flag). Use this after reviewing a transaction that doesn't need category changes. Args: transaction_id: The ID of the transaction to mark as reviewed Returns: Updated transaction details.
AI agents use mark_transaction_reviewed 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 the state of a transaction record (clearing a review flag) but does not create, delete, or destroy data irreversibly. It is a reversible update operation that changes transaction metadata. The blast radius is limited—marking a transaction as reviewed could affect financial record organization and filtering, but the operation is reversible and the underlying transaction data remains intact.
From the tool's definition mark_transaction_reviewed marks a transaction's review status by clearing the needs_review flag, which modifies transaction metadata. The tool explicitly performs an update operation, returning 'Updated transaction details.'
Documented attack patterns abuse exactly the kind of access mark_transaction_reviewed 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 mark_transaction_reviewed:
{
"version": "1",
"default": "deny",
"tools": {
"mark_transaction_reviewed": {
"limits": [
{
"counter": "mark_transaction_reviewed_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mark_transaction_reviewed 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.
Mark a transaction as reviewed (clears the needs_review flag). Use this after reviewing a transaction that doesn't need category changes. Args: transaction_id: The ID of the transaction to mark as reviewed Returns: Updated transaction details. 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 mark_transaction_reviewed: 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.
mark_transaction_reviewed 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 mark_transaction_reviewed 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 mark_transaction_reviewed. 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.
mark_transaction_reviewed 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.