iceberg-mcp-server

Name: iceberg-mcp-server
Availability: InStock
Author: Cloudera

The Cloudera Iceberg MCP Server is a Model Context Protocol server that provides read-only access to Iceberg tables via Apache Impala. This server enables large language models (LLMs) to inspect database schemas and execute read-only queries. It is primarily intended for use in database, file system, AI/LLM, and cloud environments.

GitHub

GitHub Stars

User Rating

Not Rated

Favorites

Views

Forks

Issues

Installation

Difficulty

Intermediate

Estimated Time

10-20 minutes

Requirements

Python 3.6以上

Apache Impala 最新版

Installation

Prerequisites

Required software and versions:

Python: 3.6 or higher

Apache Impala: Latest version

Installation Steps

1. Clone Repository

bash
git clone https://github.com/cloudera/iceberg-mcp-server.git
cd iceberg-mcp-server

2. Install Dependencies

bash
pip install -r requirements.txt

3. Configure Claude Desktop

Edit claude_desktop_config.json to add the MCP server:

json
{
  "mcpServers": {
    "iceberg-mcp-server": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/cloudera/iceberg-mcp-server@main",
        "run-server"
      ],
      "env": {
        "IMPALA_HOST": "coordinator-default-impala.example.com",
        "IMPALA_PORT": "443",
        "IMPALA_USER": "username",
        "IMPALA_PASSWORD": "password",
        "IMPALA_DATABASE": "default"
      }
    }
  }
}

4. Start Server

bash
uvx run-server

Troubleshooting

Common Issues

Issue: Server won't start Solution: Check Python version and dependencies. Issue: Not recognized by Claude Desktop Solution: Verify configuration file path and syntax.

Configuration

Basic Configuration

Claude Desktop Setup

Edit ~/.config/claude-desktop/claude_desktop_config.json (macOS/Linux) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json
{
  "mcpServers": {
    "iceberg-mcp-server": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/cloudera/iceberg-mcp-server@main",
        "run-server"
      ],
      "env": {
        "IMPALA_HOST": "coordinator-default-impala.example.com",
        "IMPALA_PORT": "443",
        "IMPALA_USER": "username",
        "IMPALA_PASSWORD": "password",
        "IMPALA_DATABASE": "default"
      }
    }
  }
}

Environment Variables

Set the following environment variables as needed:

bash
export IMPALA_HOST="coordinator-default-impala.example.com"
export IMPALA_PORT="443"
export IMPALA_USER="username"
export IMPALA_PASSWORD="password"
export IMPALA_DATABASE="default"

Advanced Configuration

Security Settings

Store sensitive information in environment variables

Set appropriate access permissions

Performance Tuning

Configure timeout values

Configuration Example

json
{
  "mcpServers": {
    "iceberg-mcp-server": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/cloudera/iceberg-mcp-server@main",
        "run-server"
      ],
      "env": {
        "IMPALA_HOST": "coordinator-default-impala.example.com",
        "IMPALA_PORT": "443",
        "IMPALA_USER": "username",
        "IMPALA_PASSWORD": "password",
        "IMPALA_DATABASE": "default"
      }
    }
  }
}

Examples

Basic Usage

Here are basic usage examples for the MCP server:

Using with Claude Desktop

1Verify MCP Server Startup

Open Claude Desktop and confirm that the configuration has been loaded correctly.

2Execute Basic Commands


   Available tools from this MCP server:
   - tool1: Description of tool1
   - tool2: Description of tool2

Programmatic Usage

python
Python example
import requests

def call_mcp_tool(tool_name, params):
    response = requests.post(
        'http://localhost:3000/mcp/call',
        json={
            'tool': tool_name,
            'parameters': params
        }
    )
    return response.json()

Usage example
result = call_mcp_tool('analyze', {
    'input': 'sample data',
    'options': {'format': 'json'}
})