Advertise
MCP.so
Sign In

MCP Iceberg Catalog

@ahodroj

Repository

Basic information

Category

AI & Agents

Transports

stdio

Author

ahodroj

About MCP Iceberg Catalog

MCP server for interacting with Apache Iceberg catalog from Claude, enabling data lake discovery and metadata search through a LLM prompt.

#mcp-iceberg#data-lake#metadata-search

MCP Iceberg Catalog config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-iceberg-service": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@ahodroj/mcp-iceberg-service",
        "--client",
        "claude"
      ]
    }
  }
}

MCP Iceberg Catalog tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Iceberg Catalog?

MCP Iceberg Catalog is a Model Context Protocol server implementation that provides a SQL interface for querying and managing Apache Iceberg tables through Claude Desktop. It integrates with Iceberg REST catalogs and S3-compatible storage for data lake operations.

How to use MCP Iceberg Catalog?

Install via Smithery using npx -y @smithery/cli install @ahodroj/mcp-iceberg-service --client claude or configure Claude Desktop manually by adding a claude_desktop_config.json entry with the uv command and environment variables ICEBERG_CATALOG_URI, ICEBERG_WAREHOUSE, and optionally S3_ENDPOINT, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY. Requires Python 3.10+, UV or pip, and access to an Iceberg REST catalog and S3 storage.

Key features of MCP Iceberg Catalog

  • SQL interface for Iceberg tables via Claude Desktop
  • Supports LIST TABLES, DESCRIBE TABLE, SELECT, and INSERT operations
  • Built on pyiceberg for catalog and table operations
  • Uses PyArrow for efficient data handling
  • Integrates with REST catalogs and S3-compatible storage

Use cases of MCP Iceberg Catalog

  • Querying and exploring Iceberg tables through natural language in Claude Desktop
  • Inserting data into Iceberg tables using SQL commands
  • Managing table metadata and schemas interactively
  • Building data lake applications with AI-assisted interfaces

Frequently asked questions

1

What dependencies does MCP Iceberg Catalog require?

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

2

What operations are currently supported?

The server supports LIST TABLES, DESCRIBE TABLE, SELECT, and INSERT operations. UPDATE, DELETE, CREATE TABLE, and ALTER TABLE are listed as future implementations.

3

How is data accessed and stored?

Data is stored in an Iceberg REST catalog and S3-compatible storage. The server connects via REST catalog URIs and uses PyIceberg for table operations and PyArrow for data handling.

4

What transport does the server use?

The server communicates with Claude Desktop through stdio using the Model Context Protocol.

5

Are there any known limitations?

Complex data types (arrays, maps, structs), timestamp with timezone, decimals, nested fields, batch inserts, authentication, role-based access, and transaction support are not yet implemented and are listed as future work.

Comments

More AI & Agents MCP servers

strac-mcp-dlp

strac-io

Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi

3

OpenZiti / LLM-Gateway

openziti

NetFoundry LLM Gateway is an OpenAI-compatible API proxy that routes requests across multiple LLM providers using zero-trust networking. Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load bala

93

KissCode

NickSF189

KissCode is the world's first relationship network where AI agents and people meet. Connect your agent over MCP: it gets a profile, meets other agents and real people, chats, sends virtual gifts, goes on dinner and movie

F

fhirHydrant

faulkj

Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

14

HeyLead: LinkedIn Outreach & Lead Generation MCP Server

D4umak

HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.

9
Advertise