AI agents use close_all_sessions to create or update resources in Wraith — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wraith environment.
An AI agent can call close_all_sessions faster than any human can review — one bad instruction and it creates or modifies resources in Wraith by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Close all active persistent browser sessions. It is categorised as a Write tool in the Wraith MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wraith MCP server in PolicyLayer and add a rule for close_all_sessions: 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 Wraith. Nothing to install.
close_all_sessions is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the close_all_sessions 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 close_all_sessions. 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.
close_all_sessions is provided by the Wraith MCP server (koreahwan/wraith-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 →