AI agents use send_email_notification to create or update resources in KafkaIQ — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KafkaIQ environment.
The tool performs a write-class operation by creating and sending emails via SMTP. While emails are sent (not stored locally), this is a reversible side effect in the sense that subsequent operations can delete or suppress notifications.
From the tool's definition Tool name 'send_email_notification' and description 'Send email notification using Gmail SMTP' indicate the tool creates and sends email messages, which are write operations that modify external state (recipient inboxes).
Attacks that exploit this kind of access
Send email notification using Gmail SMTP. It is categorised as a Write tool in the KafkaIQ MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the KafkaIQ MCP server in PolicyLayer and add a rule for send_email_notification: 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 KafkaIQ. Nothing to install.
send_email_notification 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 send_email_notification 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 send_email_notification. 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.
send_email_notification is provided by the KafkaIQ MCP server (ojhaayush03/kafka_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 →