Shortcut: Get total business count for a location/category (useful for market sizing)
AI agents call count_businesses to retrieve information from Yelp Fusion MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries aggregate data (business counts) for analysis purposes. It has no side effects, creates no data, executes no external commands, and does not delete or modify anything. It is purely informational retrieval suitable for market sizing research.
From the tool's definition Tool description states it retrieves 'total business count' which is a query operation. The broader server description confirms this is for 'performing market research' and 'look up businesses'.
Attacks that exploit this kind of access
Shortcut: Get total business count for a location/category (useful for market sizing). It is categorised as a Read tool in the Yelp Fusion MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Yelp Fusion MCP Server MCP server in PolicyLayer and add a rule for count_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 Fusion MCP Server. Nothing to install.
count_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 count_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 count_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.
count_businesses is provided by the Yelp Fusion MCP Server MCP server (shawndrake2/mcp-yelp). 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 →