Search for banks by describing what you are looking for in natural language. This searches across bank descriptions including services offered, history, location, unique features, and institution type. Use this when the user asks about banks with specific characteristics, services, or qualities.
AI agents call bank_semanticSearch to retrieve information from Moon Banking MCP Server 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 data from a read-only banking directory without side effects. It matches the 'Read' category definition: 'retrieves or queries data; no side effects (search, list, get, fetch).' The severity is low because misuse would only result in returning unwanted information about banks, with no financial impact, data loss, or operational consequences.
From the tool's definition Tool performs 'search' operation across bank directory data using natural language queries. Description explicitly states it 'searches across bank descriptions' and retrieves information about 'services offered, history, location, unique features, and…
Attacks that exploit this kind of access
Search for banks by describing what you are looking for in natural language. This searches across bank descriptions including services offered, history, location, unique features, and institution type. Use this when the user asks about banks with specific characteristics, services, or qualities. It is categorised as a Read tool in the Moon Banking MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Moon Banking MCP Server MCP server in PolicyLayer and add a rule for bank_semanticSearch: 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 Moon Banking MCP Server. Nothing to install.
bank_semanticSearch 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 bank_semanticSearch 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 bank_semanticSearch. 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.
bank_semanticSearch is provided by the Moon Banking MCP Server MCP server (moonbanking/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →