MCP server for Apache Gravitino(incubating)
@datastrato
About MCP server for Apache Gravitino(incubating)
MCP server for Apache Gravitino
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-gravitino": {
"command": "uv",
"args": [
"venv"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is MCP server for Apache Gravitino(incubating)?
It is an MCP server that provides a FastMCP integration for Apache Gravitino services, offering a simplified interface for metadata interaction. It supports metadata operations for catalogs, schemas, tables, models, users, tags, and user-role management. It is intended for users who want to interact with Gravitino metadata through an MCP-compatible client.
How to use MCP server for Apache Gravitino(incubating)?
Install dependencies with uv, set environment variables for the Gravitino server URI and metalake, optionally configure authentication (JWT token or basic auth), and optionally activate specific tools via GRAVITINO_ACTIVE_TOOLS. Then run the server using the provided uv command, which includes fastmcp and httpx dependencies. An example configuration for the Goose client is provided in the README.
Key features of MCP server for Apache Gravitino(incubating)
- Seamless integration with FastMCP for Gravitino APIs
- Simplified interface for metadata interaction
- Supports catalogs, schemas, tables, models, users, tags, and user-role management
- Token-based and basic authentication methods
- Tool activation via method names
- Designed to stay within LLM token limits
Use cases of MCP server for Apache Gravitino(incubating)
- Retrieve metadata about catalogs, schemas, and tables from Gravitino
- Manage tags and associate them with tables or columns
- Manage users and roles, including granting and revoking roles
- List and fetch details of models and model versions
FAQ from MCP server for Apache Gravitino(incubating)
What authentication methods are supported?
The server supports both token-based authentication (using a JWT token) and basic authentication (username/password). Set the corresponding environment variables (GRAVITINO_JWT_TOKEN or GRAVITINO_USERNAME/GRAVITINO_PASSWORD).
How do I activate only specific tools?
Set the optional environment variable GRAVITINO_ACTIVE_TOOLS to a comma-separated list of method names (e.g., get_list_of_roles). The default value * activates all tools.
What are the system requirements?
Python 3.10 or later, the uv tool for dependency management, and the fastmcp and httpx packages. The server connects to a running Apache Gravitino instance.
Is there an example configuration for the Goose client?
Yes, the README includes a JSON snippet showing how to configure the client using uv and environment variables for a Gravitino server running at http://localhost:8090.
What operations does the tool list cover?
The server provides tools for tables (list catalogs, schemas, tables, get table details/columns), tags (list, associate, list objects), user roles (list roles/users, grant/revoke), and models (list models, get model versions). It does not expose all Gravitino APIs.
More Other MCP servers
Awesome Mcp Servers
punkpeyeA collection of MCP servers.
MCP Registry
modelcontextprotocolA community driven registry service for Model Context Protocol (MCP) servers.
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
AutoBrowser MCP
autobrowser-aiBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Inbox Zero AI MCP
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Comments