AI agents call clark_list_facilities to retrieve information from Clark 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 a list of available facilities—a read-only operation that retrieves information without modifying, executing code, deleting data, or committing financial obligations. The low severity reflects that exposing facility names poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'clark_list_facilities' and description 'List the warehouse facilities Clark can produce shift plans for' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List the warehouse facilities Clark can produce shift plans for. It is categorised as a Read tool in the Clark MCP Server, which means it retrieves data without modifying state.
Register the Clark MCP server in PolicyLayer and add a rule for clark_list_facilities: 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 Clark. Nothing to install.
clark_list_facilities 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 clark_list_facilities 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 clark_list_facilities. 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.
clark_list_facilities is provided by the Clark MCP server (jarmstrong158/clark-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 →