Gravitino

v1.0.0Databasesstable

MCP server for Apache Gravitino

gravitinomcpai-integration
Share:
22
Stars
0
Downloads
0
Weekly
0/5

What is Gravitino?

Gravitino is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for apache gravitino

MCP server for Apache Gravitino

This server falls under the Databases and Data Science & ML categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP server for Apache Gravitino

Use Cases

Manage Apache Gravitino metadata catalogs through MCP.
datastrato

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 3, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx gravitino

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Gravitino

The Gravitino MCP server connects AI assistants to Apache Gravitino, the open-source unified metadata lake that manages catalogs, schemas, tables, tags, roles, and ML model versions across heterogeneous data sources. Through this server, Claude and other AI tools can list and explore metadata catalogs, retrieve column-level table details, manage user roles and permissions, apply tags to data assets, and browse registered ML model versions — all without writing Gravitino API calls directly. It is designed for data engineers and platform teams who want AI-assisted metadata governance and discovery across multi-cloud data estates.

Prerequisites

  • Apache Gravitino server running and accessible (default: http://localhost:8090)
  • Python 3.9 or later with uv installed (uv is used for dependency management)
  • Git to clone the repository
  • Gravitino credentials: either a JWT token (GRAVITINO_JWT_TOKEN) or username and password (GRAVITINO_USERNAME and GRAVITINO_PASSWORD)
  • An MCP-compatible client such as Claude Desktop or Goose
1

Clone the repository

The server is not published to PyPI, so clone it from GitHub and enter the project directory.

git clone [email protected]:datastrato/mcp-server-gravitino.git
cd mcp-server-gravitino
2

Create a virtual environment with uv

uv creates and manages a fast, reproducible virtual environment. Activate it before installing dependencies.

uv venv
source .venv/bin/activate
3

Install dependencies

Install the server and its dependencies into the virtual environment.

uv install
4

Set environment variables

Configure the required connection variables. GRAVITINO_URI and GRAVITINO_METALAKE are always required. Choose either JWT or basic auth.

export GRAVITINO_URI=http://localhost:8090
export GRAVITINO_METALAKE=metalake_demo

# JWT authentication:
export GRAVITINO_JWT_TOKEN=your_jwt_token

# OR basic auth:
export GRAVITINO_USERNAME=admin
export GRAVITINO_PASSWORD=yourpassword
5

Add to Claude Desktop config

Register the server in your MCP client configuration using uv run to invoke the server inside its virtual environment.

{
  "mcpServers": {
    "gravitino": {
      "command": "uv",
      "args": [
        "--directory", "/absolute/path/to/mcp-server-gravitino",
        "run", "--with", "fastmcp", "--with", "httpx",
        "--with", "mcp-server-gravitino",
        "python", "-m", "mcp_server_gravitino.server"
      ],
      "env": {
        "GRAVITINO_URI": "http://localhost:8090",
        "GRAVITINO_METALAKE": "metalake_demo",
        "GRAVITINO_USERNAME": "admin",
        "GRAVITINO_PASSWORD": "yourpassword"
      }
    }
  }
}

Gravitino Examples

Client configuration

Complete claude_desktop_config.json entry for the Gravitino MCP server using uv run and basic authentication.

{
  "mcpServers": {
    "gravitino": {
      "command": "uv",
      "args": [
        "--directory", "/Users/yourname/mcp-server-gravitino",
        "run", "--with", "fastmcp", "--with", "httpx",
        "--with", "mcp-server-gravitino",
        "python", "-m", "mcp_server_gravitino.server"
      ],
      "env": {
        "GRAVITINO_URI": "http://localhost:8090",
        "GRAVITINO_METALAKE": "metalake_demo",
        "GRAVITINO_USERNAME": "admin",
        "GRAVITINO_PASSWORD": "yourpassword"
      }
    }
  }
}

Prompts to try

Example queries you can ask Claude to run against your Gravitino metadata lake.

- "List all catalogs in the metalake_demo metalake"
- "Show me the schemas in the Hive catalog and describe the tables in the sales schema"
- "Get the column details for the orders table including data types and descriptions"
- "List all tags and show me which data assets are tagged as PII"
- "Show me the current user roles and who has admin permissions"
- "List the registered ML models and their latest versions"

Troubleshooting Gravitino

Connection refused when the server tries to reach GRAVITINO_URI

Verify that the Apache Gravitino server is running: curl http://localhost:8090/api/version. If Gravitino is on a remote host, update GRAVITINO_URI to the correct hostname and port. Check firewall rules if running in a container or cloud environment.

Authentication fails with 401 Unauthorized

Ensure you are using only one authentication method at a time. If GRAVITINO_JWT_TOKEN is set, GRAVITINO_USERNAME and GRAVITINO_PASSWORD are ignored. Clear both sets of variables and set only the one your Gravitino instance expects.

uv run fails with 'package not found: mcp-server-gravitino'

The --with mcp-server-gravitino flag expects the package to be installable. If it has not been published to PyPI, replace --with mcp-server-gravitino with a direct path: --with /absolute/path/to/mcp-server-gravitino, or run 'uv pip install -e .' inside the project directory first.

Frequently Asked Questions about Gravitino

What is Gravitino?

Gravitino is a Model Context Protocol (MCP) server that mcp server for apache gravitino It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Gravitino?

Follow the installation instructions on the Gravitino GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Gravitino?

Gravitino works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Gravitino free to use?

Yes, Gravitino is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Databases MCP Servers

Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "gravitino": { "command": "npx", "args": ["-y", "gravitino"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Gravitino?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides