KosmoKrator

data

Apache Kafka MCP Integration for Vercel AI SDK

Connect Apache Kafka to Vercel AI SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

7 functions 6 read 1 write API token auth
Submit Apache Kafka feedback View package source

Connect Apache Kafka to Vercel AI SDK

Use KosmoKrator as a local integration gateway for Vercel AI SDK agents and scripts.

Create an MCP client that starts or connects to the KosmoKrator gateway for the selected integration. The gateway is local, scoped to this integration, and starts with --write=deny so Vercel AI SDK can inspect read-capable tools without receiving write access by default.

Apache Kafka MCP Config for Vercel AI SDK

Prefer CLI JSON calls when a workflow only needs one deterministic integration operation.

{
  "mcpServers": {
    "kosmokrator-kafka": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=kafka",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=kafka --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Apache Kafka instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Apache Kafka Tools Visible to Vercel AI SDK

Vercel AI SDK sees stable MCP tool names generated from the Apache Kafka integration catalog.

MCP toolSource functionTypeDescription
integration__kafka__kafka_list_topics kafka.kafka_list_topics Read List Kafka topics in a cluster. Returns topic names, partition counts, replication factors, and status.
integration__kafka__kafka_get_topic kafka.kafka_get_topic Read Get full details of a specific Kafka topic by name. Returns partition count, replication factor, and topic configuration.
integration__kafka__kafka_create_topic kafka.kafka_create_topic Write Create a new Kafka topic in a cluster. Specify the topic name, partition count, and optional replication factor and configs.
integration__kafka__kafka_list_clusters kafka.kafka_list_clusters Read List Kafka clusters in your Confluent Cloud environment. Returns cluster IDs, names, types, and status.
integration__kafka__kafka_get_cluster kafka.kafka_get_cluster Read Get details of a specific Kafka cluster. Returns broker count, controller info, and cluster configuration.
integration__kafka__kafka_list_producers kafka.kafka_list_producers Read List producers for a specific Kafka topic. Returns producer IDs, client IDs, and connection details.
integration__kafka__kafka_get_current_user kafka.kafka_get_current_user Read Get the currently authenticated Confluent Cloud user. Useful for verifying credentials and identifying the connected account.

Related Apache Kafka Pages

Apache Kafka CLIUse direct JSON commands instead of MCP discovery. Apache Kafka MCPFull gateway reference and MCP tool names. KosmoKrator for Vercel AI SDKClient-level gateway setup.