AI agents use unsubscribe to create or update resources in Unfragile — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unfragile environment.
Unsubscribing cancels a persistent monitor, which is a reversible modification to subscription state (the user can re-subscribe). It modifies data (removes the watch) but is not irreversible in the destructive sense, placing it in the Write category. Severity is medium because misuse could cause an agent to lose important monitoring/alerting capabilities.
From the tool's definition "Cancel a persistent watch (monitor)" — this removes/deactivates a subscription using a monitor ID returned from subscribe
Attacks that exploit this kind of access
Cancel a persistent watch (monitor). Use the monitor ID returned from subscribe. It is categorised as a Write tool in the Unfragile MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Unfragile MCP server in PolicyLayer and add a rule for unsubscribe: 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 Unfragile. Nothing to install.
unsubscribe 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 unsubscribe 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 unsubscribe. 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.
unsubscribe is provided by the Unfragile MCP server (savirinc/unfragile-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 →