Apache Iceberg MCP server for AI agents

MCP Iceberg Catalog is a server implementation that allows you to interact with Apache Iceberg through the Model Context Protocol (MCP). It provides a SQL interface for querying and managing Iceberg tables directly from Claude Desktop, making it easy to work with your data lake using natural language.

Installation

Prerequisites

Python 3.10 or higher
UV package installer (recommended) or pip
Access to an Iceberg REST catalog and S3-compatible storage

Installation via Smithery

The easiest way to install MCP Iceberg Catalog is through Smithery:

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

Manual Installation in Claude Desktop

To manually set up the MCP Iceberg Catalog, add the following configuration to your claude_desktop_config.json file:

{
  "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"
      }
    }
  }
}

Make sure to replace the placeholder values with your actual configuration:

PATH_TO_/mcp-iceberg-service: The directory path where the MCP Iceberg service is installed
ICEBERG_CATALOG_URI: URL of your Iceberg REST catalog service
ICEBERG_WAREHOUSE: Your Iceberg warehouse name
S3_ENDPOINT: Your S3 endpoint (optional if using standard AWS S3)
AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY: Your S3 credentials

Usage

Once installed, you can use SQL commands in Claude Desktop to interact with your Iceberg tables. The service supports several operations:

Listing Tables

To view all available tables:

LIST TABLES

Describing a Table

To view the schema of a specific table:

DESCRIBE TABLE namespace.tablename

Querying Data

To query data from a table:

SELECT * FROM namespace.tablename

You can use standard SQL features like:

Column selection: SELECT column1, column2 FROM table
Filtering: SELECT * FROM table WHERE condition
Limiting results: SELECT * FROM table LIMIT 10

Inserting Data

To insert data into a table:

INSERT INTO namespace.tablename VALUES (value1, value2, ...)

Supported Features

The MCP Iceberg Catalog currently supports:

Table listing and metadata retrieval
Table schema inspection
SELECT queries with filtering and limiting
INSERT operations for adding new data

When using Claude Desktop, you can interact with these features using natural language, and Claude will translate your requests into the appropriate SQL commands for the MCP server.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "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"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "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"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "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"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect