AI agents use manage_forms 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.
The manage_forms tool spans Read (list forms, list_subscribers) and Write (add_subscriber) categories. The add_subscriber action creates new records and triggers opt-in workflows, which are reversible modifications to the subscriber database. This is Write-level risk.
From the tool's definition Tool performs 'add_subscriber' action which creates new subscriber records and 'triggers double opt-in if enabled', modifying Kit.com's subscriber database. Also lists forms and their subscriber data (Read component), but the Write action dominates.
Attacks that exploit this kind of access
Manage Kit forms — list all forms, list subscribers who opted in through a form, or add a subscriber to a form (triggers double opt-in if enabled). Actions: list, list_subscribers, add_subscriber. 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_forms: 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_forms 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_forms 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_forms. 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_forms 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 →