This record as markdown: /tools/io-github-portel-dev-ncp/consume.md
What consume does on Ncp
AI agents invoke consume to trigger actions in Ncp. 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.
Why consume is rated High
Consuming messages from Kafka is not a simple passive read; it advances the consumer group offset, which is a side effect that affects the state of the Kafka topic for that consumer group. This makes it more than a pure Read — it is an external operation that changes consumer state.
From the tool's definition "Consume messages from Kafka topic" — triggers an external read/polling operation against a Kafka broker, initiating an active connection and consuming (dequeuing) messages from a topic stream.
Attacks that exploit this kind of access
The rule that runs consume safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ncp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For consume, this is the rule to start with:
consume stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ncp, apply this rule, and every consume call is checked against it from then on.
Questions about consume
Consume messages from Kafka topic. It is categorised as a Execute tool in the Ncp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ncp MCP server in PolicyLayer and add a rule for consume: 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 Ncp. Nothing to install.
consume 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 consume 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 consume. 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.
consume is provided by the Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ncp, and thousands of servers like it.
This server
Across the catalogue