{"type":"mcp_server","name":"mcp-kafka","description":"mcp-kafka bridges AI assistants and Kafka, enabling interaction with Kafka clusters through the Model Context Protocol. It allows AI to manage topics, produce messages, and consume data directly from Kafka.","category":"Communication","language":"Go","stars":80,"forks":0,"owner":"kanapuli","github_url":"https://github.com/kanapuli/mcp-kafka","homepage":null,"setup":"## Setup\n\n### Prerequisites\n- Go 1.24 or higher\n- A running Kafka cluster (default connection: localhost:9092)\n\n### Building from Source\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/kanapuli/mcp-kafka.git\n   cd mcp-kafka\n   ```\n\n2. Build the application:\n   ```bash\n   make build\n   ```\n\n3. Optionally, build for a specific platform:\n   ```bash\n   make build GOOS=darwin GOARCH=arm64\n   ```\n\n### Installing as a Claude Desktop Tool\n1. Build the application as mentioned above.\n\n2. Place the executable in a location included in your system PATH or in a dedicated tools directory.\n\n3. Please follow this [Claude Desktop Tool Installation Guide](https://modelcontextprotocol.io/quickstart/user) to install the tool.\n\nThe JSON to be added to the claude_desktop_config.json file is as follows, Use the right username and password for SASL login. Leave them empty for PLAINTEXT authentication.\n\n```json\n{\n  \"mcpServers\": {\n    \"kafka\": {\n\t    \"command\": \"/Your-mcp-kafka-executable-path/mcp-kafka-darwin-arm64\",\n      \"args\": [\n          \"--bootstrap-servers=localhost:9092\",\n          \"--consumer-group-id=mcp-kafka-consumer-group\",\n          \"--username=\",\n          \"--password=\"\n        ],\n      \"env\": {}\n    }\n  }\n}\n```","tools":"## Available Tools\n\n1. Create Topic (Create a new Kafka topic with configurable partitions and replication factor)\n2. List Topics (Get a list of all available Kafka topics in the cluster)\n3. Delete Topic (Remove an existing Kafka topic)\n4. Describe Topic (Get detailed information about a specific topic, including partition details)\n5. Produce Message (Send messages to a Kafka topic with support for message keys and headers)\n6. Consume Messages (Read messages from a Kafka topic with configurable timeout)","faq":null,"created_at":"2025-03-15T14:58:46+00:00","updated_at":"2025-03-24T10:01:01+00:00","source_url":"https://model-context-protocol.com/servers/ai-kafka-model-context-protocol-server","related_articles":[]}