AI agents invoke upstash_kafka_produce to trigger actions in UnClick. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
email | string | Yes | |
topic | string | Yes | |
api_key | string | Yes | |
messages | string | Yes | JSON array of message objects [{value: '...'}] |
cluster_id | string | Yes |
Parameters from the server's own tool schema.
Producing messages to a message queue is an Execute action—it runs an external operation (publishing to Kafka) whose effects depend on the arguments (message content, topic, etc.). While it's not destructive or financial by itself, an AI agent could misuse this to send malicious messages, trigger downstream systems, or cause operational disruption.
From the tool's definition Tool description states 'Produce messages to an Upstash Kafka topic.' The action of producing/publishing messages to a Kafka topic is an external operation that triggers message distribution with effects determined by the message content provided as arguments.
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
Produce messages to an Upstash Kafka topic. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
upstash_kafka_produce accepts 5 parameters: email, topic, api_key, messages, cluster_id. Required: email, topic, api_key, messages, cluster_id. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for upstash_kafka_produce: 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 UnClick. Nothing to install.
upstash_kafka_produce is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the upstash_kafka_produce 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 upstash_kafka_produce. 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.
upstash_kafka_produce is provided by the UnClick MCP server (@unclick/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 →