AI agents use track_event to create or update resources in Iterable MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Iterable MCP Server environment.
Tracking a custom event creates a new event record associated with a user in the Iterable platform. This is a Write operation as it creates data (event records) that could influence downstream marketing automations, campaign triggers, and user segmentation. While it can trigger downstream effects, the primary action is recording/creating an event entry.
From the tool's definition Track a custom event for a user
Documented attack patterns abuse exactly the kind of access track_event gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Iterable MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for track_event:
{
"version": "1",
"default": "deny",
"tools": {
"track_event": {
"limits": [
{
"counter": "track_event_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}track_event stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Track a custom event for a user. It is categorised as a Write tool in the Iterable MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Iterable MCP Server MCP server in PolicyLayer and add a rule for track_event: 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 Iterable MCP Server. Nothing to install.
track_event 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 track_event 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 track_event. 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.
track_event is provided by the Iterable MCP Server MCP server (iterable/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Iterable MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
78 Iterable MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.