kafka_produce_message · MCP Kafka MCP: Risk & Policy

WHAT IT DOES

What kafka_produce_message does on MCP Kafka

AI agents use kafka_produce_message to create or update resources in MCP Kafka — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Kafka environment.

WHY IT NEEDS A POLICY

Why kafka_produce_message needs a policy

This tool writes/publishes a message to a Kafka topic. It creates new data in the message queue but does not delete or overwrite existing messages. Misuse could flood topics with bad data or trigger unintended downstream consumers, giving it medium severity.

From the tool's definition 'Produce a message to a Kafka topic (requires write access)'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kafka_produce_message Rate-limited

kafka_produce_message 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "kafka_produce_message": {
      "limits": [
        {
          "counter": "kafka_produce_message_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Kafka, so you can run agents against it safely.

FAQ

Questions about kafka_produce_message

What does the kafka_produce_message tool do? +

Produce a message to a Kafka topic (requires write access). It is categorised as a Write tool in the MCP Kafka MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on kafka_produce_message? +

Register the MCP Kafka MCP server in PolicyLayer and add a rule for kafka_produce_message: 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 MCP Kafka. Nothing to install.

What risk level is kafka_produce_message? +

kafka_produce_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit kafka_produce_message? +

Yes. Add a rate_limit block to the kafka_produce_message 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.

How do I block kafka_produce_message completely? +

Set action: deny in the PolicyLayer policy for kafka_produce_message. 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.

What MCP server provides kafka_produce_message? +

kafka_produce_message is provided by the MCP Kafka MCP server (williajm/mcp_kafka). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.