Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

mcp-server-gravitino

MCP.Pizza Chef: datastrato

The mcp-server-gravitino is an MCP server that integrates Apache Gravitino(incubating) APIs with FastMCP, providing a streamlined interface for managing metadata. It supports catalog, schema, table metadata, as well as tag and user-role information, enabling efficient metadata operations within the MCP ecosystem. This server is built with Python 3.10+ and facilitates easy integration of Gravitino services into MCP workflows.

Use This MCP server To

Manage catalog, schema, and table metadata via MCP Integrate Apache Gravitino services with FastMCP workflows Handle user-role and tag metadata in data catalogs Enable metadata-driven AI workflows with real-time context Provide structured metadata access for LLM-powered applications

README

MCP server for Apache Gravitino(incubating)

Python Version

MCP server providing Gravitino APIs - A FastMCP integration for Apache Gravitino(incubating) services.

Features

  • Gravitino API integration with FastMCP
  • Easy-to-use interface for metadata management
  • Support for catalog/schema/table metadata, tag, and user-role information

Installation

from configuration

{
    "mcpServers": {
        "Gravitino": {
            "command": "uv",
            "args": [
              "--directory",
              "/Users/user/workspace/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_USERNAME": "admin",
                "GRAVITINO_PASSWORD": "admin",
                "GRAVITINO_METALAKE": "metalake_demo"
            }
        }
    }
}

Environment Variables

Authorization

mcp-server-gravitino provides token auth and basic auth:

Token Auth

GRAVITINO_URI=http://localhost:8090
GRAVITINO_JWT_TOKEN=<YOUR GRAVITINO JWT TOKEN>

Basic Auth

GRAVITINO_URI=http://localhost:8090
GRAVITINO_USERNAME=<YOUR GRAVITINO USERNAME>
GRAVITINO_PASSWORD=<YOUR GRAVITINO PASSWORD>

Tool list

mcp-server-gravitino does not provide all APIs available in Gravitino.

Table Tools

  • get_list_of_catalogs: Get a list of catalogs with basic information
  • get_list_of_schemas: Get a list of schemas with basic information
  • get_list_of_tables: Get a paginated list of tables with basic information
  • get_table_by_fqn: Get detailed table information by fully qualified name
  • get_table_columns_by_fqn: Get table columns information by fully qualified name

Tag Tools

  • get_list_of_tags: Get a list of tags with basic information
  • associate_tag_to_table: Associate a tag to a table
  • associate_tag_to_column: Associate a tag to a column
  • list_objects_by_tag: Get a list of objects associated with a tag

User Role Tools

  • get_list_of_roles: Get a list of roles with basic information
  • get_list_of_users: Get a list of users with basic information
  • grant_role_to_user: Grant a role to a user
  • revoke_role_from_user: Revoke a role from a user

Each tool returns optimized responses with relevant fields to ensure compatibility with model context limits while providing essential metadata information.

License

This project is open source software licensed as Apache License Version 2.0.

mcp-server-gravitino FAQ

How do I install the mcp-server-gravitino?
Install by configuring the MCP server with the provided JSON snippet and running the Python module mcp_server_gravitino.server using Python 3.10+.
What metadata types does mcp-server-gravitino support?
It supports catalog, schema, table metadata, tags, and user-role information for comprehensive metadata management.
Which Python version is required for mcp-server-gravitino?
Python 3.10 or higher is required to run the mcp-server-gravitino.
How does mcp-server-gravitino integrate with FastMCP?
It uses FastMCP to provide a fast, easy-to-use interface for exposing Gravitino APIs as MCP services.
Can mcp-server-gravitino be used to manage user roles?
Yes, it supports managing user-role metadata alongside other catalog metadata.
Is mcp-server-gravitino suitable for production use?
As it is marked incubating, it is suitable for development and testing; evaluate stability before production deployment.
What protocols or libraries does mcp-server-gravitino use?
It uses FastMCP and HTTPX libraries to serve Gravitino APIs efficiently.