AI agents call capture_status to retrieve information from Arkime 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 cluster and health status information from Arkime. It performs read-only operations to obtain metadata about the capture system's current state. There are no side effects, data modifications, code execution, deletions, or financial implications.
From the tool's definition Tool name 'capture_status' and description 'Get current Arkime capture health — cluster status, node count, shard health' indicate retrieval of monitoring/status information with no modification or execution capability.
Attacks that exploit this kind of access
Get current Arkime capture health — cluster status, node count, shard health,. It is categorised as a Read tool in the Arkime MCP Server, which means it retrieves data without modifying state.
Register the Arkime MCP server in PolicyLayer and add a rule for capture_status: 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 Arkime. Nothing to install.
capture_status 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 capture_status 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 capture_status. 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.
capture_status is provided by the Arkime MCP server (swannman/arkime-mcp-server). 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 →