Get transactions from Monarch Money. Args: limit: Number of transactions to retrieve (default: 100) offset: Number of transactions to skip (default: 0) start_date: Start date in YYYY-MM-DD format end_date: End date in YYYY-MM-DD format account_id: Specific account ID to filter by (deprecated, use...
AI agents call get_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 or queries transaction data with no side effects. It performs read-only operations, matching the Read category definition. Severity is low because exposure of financial transaction data, while sensitive, does not directly move money, delete records, or execute arbitrary code. The blast radius is limited to information disclosure.
From the tool's definition Tool name is 'get_transactions' and description states 'Get transactions from Monarch Money.' The parameters (limit, offset, start_date, end_date, account_id, search, category_ids, etc.) are all filtering/query parameters used to retrieve data without…
Documented attack patterns abuse exactly the kind of access get_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 get_transactions:
{
"version": "1",
"default": "deny",
"tools": {
"get_transactions": {}
}
}get_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.
Get transactions from Monarch Money. Args: limit: Number of transactions to retrieve (default: 100) offset: Number of transactions to skip (default: 0) start_date: Start date in YYYY-MM-DD format end_date: End date in YYYY-MM-DD format account_id: Specific account ID to filter by (deprecated, use account_ids) search: Search query to filter transactions category_ids: List of category IDs to filter by category_group_ids: List of category group IDs to filter by account_ids: List of account IDs to filter by tag_ids: List of tag IDs to filter by has_notes: Filter for transactions with/without notes is_split: Filter for split transactions is_recurring: Filter for recurring transactions wide_search: Opt-in fallback that pulls a page of transactions and filters them locally across description, original statement, plaid name, notes, merchant, category, account, and tags when Monarch's server-side search returns empty or errors. Off by default because it can be expensive; turn on when a search you expect to match comes back empty. search_scan_limit: Maximum transactions the wide_search fallback will scan locally (default 200). 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 get_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.
get_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 get_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 get_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.
get_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.