AI agents call list_warehouses to retrieve information from Keycrm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns configuration data about warehouses without creating, modifying, deleting, or executing any operations. It is purely informational, making it a Read category tool. Severity is low because warehouse directory information poses minimal risk even if exposed to an AI agent — it cannot manipulate inventory, finances, or customer data.
From the tool's definition Tool name is 'list_warehouses' and description states 'List all warehouses configured in keyCRM' — this is a retrieval operation that returns warehouse metadata (IDs, names, addresses) with no modification or side effects.
Attacks that exploit this kind of access
List all warehouses configured in keyCRM with their IDs, names, and addresses. It is categorised as a Read tool in the Keycrm MCP Server, which means it retrieves data without modifying state.
Register the Keycrm MCP server in PolicyLayer and add a rule for list_warehouses: 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 Keycrm. Nothing to install.
list_warehouses 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 list_warehouses 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 list_warehouses. 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.
list_warehouses is provided by the Keycrm MCP server (ivanklymenko/keycrm-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 →