AI agents invoke session_cancel to trigger actions in Iris MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Cancelling a running operation is an active intervention that terminates an in-progress process. This is an Execute-category action because it triggers an external operation (stopping a session), and its effects depend on what session is targeted. It is not purely destructive (it doesn't delete data irreversibly) but it does affect the runtime state of a session, making Execute the most appropriate category.
From the tool's definition Cancel a running session operation
Attacks that exploit this kind of access
Cancel a running session operation. It is categorised as a Execute tool in the Iris MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Iris MCP server in PolicyLayer and add a rule for session_cancel: 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 Iris MCP. Nothing to install.
session_cancel is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the session_cancel 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 session_cancel. 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.
session_cancel is provided by the Iris MCP server (jenova-marie/iris-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 →