Check if a topic exists.
AI agents call topic_exists 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.
This tool performs a read-only query against Kafka metadata to determine topic existence. It does not create, modify, delete, or execute any operations—it only retrieves information. The blast radius if misused is minimal; an agent could only consume unnecessary metadata API calls but cannot cause harm to data or infrastructure.
From the tool's definition Tool name 'topic_exists' and description 'Check if a topic exists' indicate a query/verification operation with no side effects. This is a simple existence check that retrieves state information from Kafka brokers.
Attacks that exploit this kind of access
Check if a topic exists. 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 topic_exists: 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.
topic_exists 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 topic_exists 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 topic_exists. 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.
topic_exists is provided by the Kafka MCP Server MCP server (shivamxtech/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 →