Cancel a running session
AI agents call cancel_session to permanently remove resources in Shannon MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a session terminates it and cannot be undone; any in-progress operations, state, or intermediate results are lost. This is irreversible, placing it in the Destructive category. Severity is high because it can disrupt active multi-agent collaborative workflows managed by the Claude Code CLI.
From the tool's definition "Cancel a running session" — cancelling a running session is an irreversible action that terminates and removes an active session, potentially losing in-progress work or state.
Attacks that exploit this kind of access
Cancel a running session. It is categorised as a Destructive tool in the Shannon MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Shannon MCP server in PolicyLayer and add a rule for cancel_session: 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 Shannon MCP. Nothing to install.
cancel_session is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cancel_session 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 cancel_session. 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.
cancel_session is provided by the Shannon MCP server (krzemienski/shannon-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 →