search_businesses
AI agents call search_businesses to retrieve information from Yelp Mcp Min without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite empty tool description, the name and context strongly indicate this retrieves or queries business data from the Yelp API without modifying, deleting, or executing operations. The naming pattern aligns with read-only search operations typical of data lookup APIs.
From the tool's definition Tool name 'search_businesses' combined with server description indicating 'business search' capability; sibling tools include 'get_business', 'get_business_reviews', 'match_business'—all retrieval operations with no side effects.
Attacks that exploit this kind of access
search_businesses. It is categorised as a Read tool in the Yelp Mcp Min MCP Server, which means it retrieves data without modifying state.
Register the Yelp Mcp Min MCP server in PolicyLayer and add a rule for search_businesses: 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 Yelp Mcp Min. Nothing to install.
search_businesses 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_businesses 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_businesses. 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_businesses is provided by the Yelp Mcp Min MCP server (miqui/yelp-mcp-min). 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 →