AI agents use manage_subscribers to create or update resources in Kit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kit environment.
This tool modifies subscriber data reversibly (subscribers can be added, updated, or re-added). While it creates or alters data, it does not irreversibly delete records (which would be Destructive) nor does it execute arbitrary code (Execute). The blast radius is high because bulk modifications to subscriber lists could disrupt marketing campaigns, trigger unintended communications, or alter customer segmentation.
From the tool's definition Tool name 'manage_subscribers' and description indicates it 'Manage Kit subscribers,' which encompasses creation, modification, and administration of subscriber records.
Attacks that exploit this kind of access
Manage Kit subscribers. To find most engaged subscribers, use. It is categorised as a Write tool in the Kit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kit MCP server in PolicyLayer and add a rule for manage_subscribers: 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 Kit. Nothing to install.
manage_subscribers 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 manage_subscribers 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 manage_subscribers. 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.
manage_subscribers is provided by the Kit MCP server (@dancumberland/kit-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 →