kafka-schema-reg

This MCP server exposes a Python-based Kafka Schema Registry management toolset via the MCP 2025-06-18 spec. It enables Claude Desktop and other MCP clients to manage multiple Kafka Schema Registry instances, organize contexts for production/staging, migrate schemas across registries, and export schemas in JSON or Avro IDL formats for backup and documentation. Typical workflows include listing contexts, registering or updating schemas, migrating schemas between registries, and exporting registry state for audits. The server integrates with Claude’s MCP tools and supports SLIM_MODE for reduced tool overhead when you don’t need full admin capabilities.

Prerequisites:

• Python 3.10+ and pip
• Git
• Access to a Kafka Schema Registry instance (or start the included test registry via Docker if desired)

Option A: Install locally (Python)

# 1) Clone the repository
git clone https://github.com/aywengo/kafka-schema-reg-mcp.git
cd kafka-schema-reg-mcp

# 2) Install dependencies
pip install -r requirements.txt

# 3) Run the MCP server (unified Python entrypoint)
python kafka_schema_registry_unified_mcp.py

Option B: Run via Docker (if you prefer containerized deployment)

docker pull aywengo/kafka-schema-reg-mcp:stable
# Example: start with minimal environment for a local registry
docker run -e SCHEMA_REGISTRY_URL=http://localhost:8081 aywengo/kafka-schema-reg-mcp:stable

Option C: Docker Compose (includes a test Schema Registry)

docker-compose up -d

Note: The README indicates a recommended docker-based deployment and a local Python execution path; choose the option that best fits your environment.

Environment variables:

• SCHEMA_REGISTRY_URL: URL of the Kafka Schema Registry instance (e.g., http://localhost:8081)
• SCHEMA_REGISTRY_USER: Optional user for registry authentication
• SLIM_MODE (when using Docker): Enable reduced tool set for faster responses Common issues:
• Ensure the Kafka Schema Registry is reachable at the URL provided by SCHEMA_REGISTRY_URL
• If running locally, expose the registry port and network accordingly
• When using Docker, consider SLIM_MODE for production-readonly workflows to minimize tool overhead Configuration tips:
• Use multiple contexts to isolate production vs. staging registries
• Export formats (JSON, Avro IDL) are useful for backups and documentation