Get the list of all Kaspi cities in Kazakhstan.
AI agents call get_cities to retrieve information from Kaspi Merchant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool simply retrieves a static or semi-static list of cities. It performs no modifications, deletions, executions, or financial operations. Even though it operates on a production system (as noted in the server description), the actual operation is purely informational retrieval with no capability to alter data or trigger external actions.
From the tool's definition Tool name 'get_cities' and description 'Get the list of all Kaspi cities in Kazakhstan' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the list of all Kaspi cities in Kazakhstan. It is categorised as a Read tool in the Kaspi Merchant MCP Server, which means it retrieves data without modifying state.
Register the Kaspi Merchant MCP server in PolicyLayer and add a rule for get_cities: 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 Kaspi Merchant. Nothing to install.
get_cities 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_cities 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_cities. 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_cities is provided by the Kaspi Merchant MCP server (theyahia/kaspi-merchant-mcp). 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 →