AI agents call clark_calendar_check 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.
The naming convention and context of sibling tools indicate this is likely a query/retrieval operation with no side effects. However, the missing description and unfamiliar tool name reduce confidence. Assigned Read as the most probable category, with low-to-medium confidence due to insufficient evidence. No destructive, financial, or clearly executable operations are evident from the name alone.
From the tool's definition Tool name 'clark_calendar_check' suggests querying calendar or scheduling data. Description is empty, limiting certainty.
Attacks that exploit this kind of access
clark_calendar_check. 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_calendar_check: 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_calendar_check 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_calendar_check 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_calendar_check. 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_calendar_check 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 →