AI agents call get_merchant 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.
The tool appears to retrieve merchant information from the Monarch Money API without side effects. No evidence of data creation, modification, or deletion. The low severity reflects the read-only nature and minimal blast radius if misused—an AI agent could only query existing merchant data.
From the tool's definition Tool name 'get_merchant' indicates retrieval of merchant data with no modification capability. The empty description limits certainty, but contextual analysis of sibling tools (which include create_*, delete_*, and categorize_* operations) and the naming…
Documented attack patterns abuse exactly the kind of access get_merchant 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_merchant:
{
"version": "1",
"default": "deny",
"tools": {
"get_merchant": {}
}
}get_merchant 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_merchant. 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_merchant: 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_merchant 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_merchant 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_merchant. 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_merchant 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.