live_messages
AI agents call live_messages to retrieve information from Kafka MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name suggests streaming or reading live messages from Kafka topics, which is a Read operation with no data modification. However, the empty description prevents full certainty. Severity is medium because reading Kafka messages could expose sensitive data depending on topic content and access controls, but it is not destructive or financial.
From the tool's definition Tool name 'live_messages' and context of sibling tools (tail_messages, consumer_group_lag, list_topics) indicate message consumption/streaming. Description is empty, reducing confidence.
Attacks that exploit this kind of access
live_messages. It is categorised as a Read tool in the Kafka MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kafka MCP Server MCP server in PolicyLayer and add a rule for live_messages: 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 Kafka MCP Server. Nothing to install.
live_messages is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the live_messages 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 live_messages. 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.
live_messages is provided by the Kafka MCP Server MCP server (jilanisayyad/kafka-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 →