AI agents call clark_get_plan 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 retrieves existing shift plan information for a warehouse workforce management system. It has no side effects—it only fetches read-only data about worker assignments. The local offline nature and context (workforce planning) confirm this is a data retrieval operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'clark_get_plan' and description 'Clark's opening shift plan for a facility: each worker's assigned' indicates retrieval of scheduling/staffing data. No mutations, deletions, or external operations are performed.
Attacks that exploit this kind of access
Clark's opening shift plan for a facility: each worker's assigned. 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_get_plan: 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_get_plan 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_get_plan 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_get_plan. 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_get_plan 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 →