AI agents call get_topic to retrieve information from Lenses MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves metadata or configuration about a Kafka topic. This is a standard read operation with no ability to modify state, delete data, execute code, or trigger destructive actions. The blast radius of accidental misuse is minimal—an agent could only gather information already accessible via legitimate queries.
From the tool's definition Tool name is 'get_topic' and description states 'Retrieve information about a specific topic' — purely retrieves data with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_topic gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lenses MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_topic:
{
"version": "1",
"default": "deny",
"tools": {
"get_topic": {}
}
}get_topic is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve information about a specific topic. It is categorised as a Read tool in the Lenses MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Lenses MCP Server MCP server in PolicyLayer and add a rule for get_topic: 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 Lenses MCP Server. Nothing to install.
get_topic 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 get_topic 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 get_topic. 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.
get_topic is provided by the Lenses MCP Server MCP server (lensesio/lenses-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Lenses MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
42 Lenses MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.