LABSCO SUMMARY

Four SQL operations today, and the author lists what is not there yet.

List, describe, select and insert are enough to explore a lake and add rows, and describe is what lets a model write a correct query rather than guess at columns. The repository is explicit about the gaps: UPDATE, DELETE, CREATE TABLE and ALTER TABLE are unimplemented, complex types such as arrays, maps and structs are not supported yet, and there is no authentication layer of its own — the credentials in the environment are the whole access model.

What it is

A Python server that turns an Iceberg REST catalog into a SQL surface. Queries are parsed with sqlparse and executed through PyIceberg, with PyArrow handling the data and type conversion in between.

What you get

LIST TABLES to see what the catalog holds
DESCRIBE TABLE for a table's schema and field types
SELECT for reading data, with scanning and filtering handled by PyIceberg
INSERT for writing rows, converted through PyArrow tables
Namespace and catalog metadata handled for you rather than passed on every call

Requirements

Python 3.10 or higher, the uv installer, and access to an Iceberg REST catalog with S3-compatible storage. Configuration is environment variables: ICEBERG_CATALOG_URI for the catalog, ICEBERG_WAREHOUSE for the warehouse name, and S3_ENDPOINT, AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY for storage. Launch as uv --directory <YOUR_PATH_TO>/mcp-iceberg-service run mcp-server-iceberg. The Python package is mcp-server-iceberg, version 0.1.0.

Setup effort

Build from source

See installation options

USE CASES

01

Exploring a data lake you did not build

List the tables and read their schemas before writing any query.

02

Answering a question from lake data

Describe what you want and let the SELECT be written and executed for you.

03

Adding rows to a table

Insert through the same interface rather than writing a PyIceberg script.

BEFORE YOU INSTALL

What to know first

Requires

uv on PATH
Python 3.10 or later
AWS_ACCESS_KEY_ID in your environment
AWS_SECRET_ACCESS_KEY in your environment

Where it runs

The documented client runs the server on your machine.

INSTALLATION

Connect your client

Server setup

TERMINAL

git clone https://github.com/ahodroj/mcp-iceberg-service.git

MCP Clients

Claude Desktop — local build

CLAUDE DESKTOP — LOCAL BUILD · JSON

{
  "mcpServers": {
    "iceberg": {
      "command": "uv",
      "args": [
        "--directory",
        "<YOUR_PATH_TO>/mcp-iceberg-service",
        "run",
        "mcp-server-iceberg"
      ],
      "env": {
        "ICEBERG_CATALOG_URI": "http://localhost:8181",
        "ICEBERG_WAREHOUSE": "<YOUR_ICEBERG_WAREHOUSE>",
        "S3_ENDPOINT": "OPTIONAL IF USING S3",
        "AWS_ACCESS_KEY_ID": "<YOUR_AWS_ACCESS_KEY_ID>",
        "AWS_SECRET_ACCESS_KEY": "<YOUR_AWS_SECRET_ACCESS_KEY>"
      }
    }
  }
}

<YOUR_PATH_TO>/mcp-iceberg-service is the absolute path of your clone, and set the env values for your own Iceberg REST catalog and S3-compatible storage (S3_ENDPOINT only if your storage needs one).

MCP Iceberg Catalog