MCP Iceberg Catalog

A MCP (Model Context Protocol) server implementation for interacting with Apache Iceberg. This server provides a SQL interface for querying and managing Iceberg tables through Claude desktop.

Claude Desktop as your Iceberg Data Lake Catalog

How to Install in Claude Desktop

Installing via Smithery

To install MCP Iceberg Catalog for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @ahodroj/mcp-iceberg-service --client claude

1. Prerequisites

2. How to install in Claude Desktop

Add the following configuration to `claude_desktop_config.json`:

{
  "mcpServers": {
    "iceberg": {
      "command": "uv",
      "args": [
        "--directory",
        "PATH_TO_/mcp-iceberg-service",
        "run",
        "mcp-server-iceberg"
      ],
      "env": {
        "ICEBERG_CATALOG_URI" : "http://localhost:8181",
        "ICEBERG_WAREHOUSE" : "YOUR ICEBERG WAREHOUSE NAME",
        "S3_ENDPOINT" : "OPTIONAL IF USING S3",
        "AWS_ACCESS_KEY_ID" : "YOUR S3 ACCESS KEY",
        "AWS_SECRET_ACCESS_KEY" : "YOUR S3 SECRET KEY"
      }
    }
  }
}

Design

Architecture

The MCP server is built on three main components:

1. MCP Protocol Handler

2. Query Processor

3. Iceberg Integration

PyIceberg Integration

The server utilizes PyIceberg in several ways:

1. Catalog Management

2. Data Operations

3. Query Execution

Further Implementation Needed

1. Query Operations

2. Data Types

3. Performance Improvements

4. Security Features

5. Monitoring and Management

6. Error Handling