AI agents call clark_explain_decision 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 retrieves and presents explanations of decisions made by the workforce RL agent Clark, along with facility rules and vocabulary for grounding. There are no indications of data modification, deletion, code execution, or financial operations. It reads existing plan data and rules to provide a natural-language explanation, fitting the Read category (retrieve/query data with no side effects).
From the tool's definition Tool name 'clark_explain_decision' and description indicate retrieval of Clark's plan and facility rules/vocabulary for explanation purposes. The verb 'explain' and grounding context suggest querying/retrieving existing data without modification.
Attacks that exploit this kind of access
Clark's plan plus the facility's rules/vocabulary as grounding so. 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_explain_decision: 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_explain_decision 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_explain_decision 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_explain_decision. 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_explain_decision 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 →