AI agents call find_companies to retrieve information from Kula Ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from a company database without creating, modifying, or deleting data. Searching a catalog is a read-only operation with minimal security risk, even in a recruiting context. The blast radius of misuse is low—an attacker could enumerate companies but cannot manipulate recruiting data or commit harmful actions.
From the tool's definition Tool name 'find_companies' combined with description 'Search the global company catalog' indicates a query/search operation with no modification or side effects.
Attacks that exploit this kind of access
Search the global company catalog. Returned IDs map to. It is categorised as a Read tool in the Kula Ai MCP Server, which means it retrieves data without modifying state.
Register the Kula Ai MCP server in PolicyLayer and add a rule for find_companies: 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 Kula Ai. Nothing to install.
find_companies 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 find_companies 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 find_companies. 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.
find_companies is provided by the Kula Ai MCP server (kula-ai/kula-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 →