Search and filter transactions with comprehensive filtering options. This is the most flexible transaction query tool, supporting all available filters. Args: search: Text to search for in transaction descriptions/merchants limit: Maximum number of transactions to return (default: 100) offset: Nu...
AI agents call search_transactions to retrieve information from Monarch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries transaction data with no side effects. It supports filtering and pagination but does not create, modify, delete, or execute operations. The action is purely informational retrieval, fitting the Read category at low severity since accessing transaction data via search has minimal blast radius compared to destructive or financial operations.
From the tool's definition Tool description states 'Search and filter transactions with comprehensive filtering options' and 'query tool, supporting all available filters.' Parameters include search, limit, offset, start_date, end_date, category_ids, account_ids—all read-only filters…
Documented attack patterns abuse exactly the kind of access search_transactions 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 search_transactions:
{
"version": "1",
"default": "deny",
"tools": {
"search_transactions": {}
}
}search_transactions is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search and filter transactions with comprehensive filtering options. This is the most flexible transaction query tool, supporting all available filters. Args: search: Text to search for in transaction descriptions/merchants limit: Maximum number of transactions to return (default: 100) offset: Number of transactions to skip for pagination (default: 0) start_date: Filter start date in YYYY-MM-DD format end_date: Filter end date in YYYY-MM-DD format category_ids: List of category IDs to filter by account_ids: List of account IDs to filter by tag_ids: List of tag IDs to filter by has_attachments: Filter for transactions with/without attachments has_notes: Filter for transactions with/without notes hidden_from_reports: Filter for transactions hidden/shown in reports is_split: Filter for split/non-split transactions is_recurring: Filter for recurring/non-recurring transactions Returns: List of matching transactions with full details. It is categorised as a Read tool in the Monarch MCP Server, which means it retrieves data without modifying state.
Register the Monarch MCP server in PolicyLayer and add a rule for search_transactions: 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.
search_transactions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_transactions 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 search_transactions. 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.
search_transactions 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.