Gravitino MCP Server Integration

What does “Gravitino” MCP Server do?

The Gravitino MCP Server is a Model Context Protocol (MCP) server that provides seamless integration between AI assistants and Apache Gravitino (incubating) services. By exposing Gravitino APIs, this server enables external AI tools and workflows to interact with metadata components such as catalogs, schemas, tables, and more. Gravitino MCP Server acts as a powerful bridge, allowing developers and AI agents to perform metadata operations, query structural information, and manage user roles efficiently. The server simplifies complex metadata operations by providing a standardized interface, making it easier to integrate data platform management tasks directly within AI-driven development environments or automated flows.

List of Prompts

No prompt templates are explicitly mentioned in the provided documentation.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No explicit list of resources is mentioned in the documentation.

List of Tools

• get_list_of_catalogs: Retrieve a list of catalogs from the Gravitino instance.
• get_list_of_schemas: Retrieve a list of schemas across the catalogs.
• get_list_of_tables: Retrieve a paginated list of tables available in the schema(s).

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Metadata Discovery: Enables developers and AI agents to efficiently list and explore catalogs, schemas, and tables within Apache Gravitino, supporting data governance and documentation workflows.
• Automated Data Platform Integration: Simplifies connecting external systems or AI workflows to Gravitino for real-time metadata queries, reducing manual API calls.
• Role-Based Access Management: Through user and role management tools (referenced in the features), developers can integrate access control workflows.
• AI-Assisted Data Exploration: Allows AI assistants to surface available data structures, supporting intelligent code suggestions or data analysis pipelines.
• Workflow Automation: Integrate metadata operations into automated pipelines, such as syncing schema changes or auditing table structures.

How to set it up

Windsurf

1. Prerequisites: Ensure you have Node.js and the uv tool installed.
2. Locate configuration: Open your Windsurf configuration file.
3. Add Gravitino MCP Server: Insert the following JSON snippet under your mcpServers section:

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

4. Edit environment variables: Replace GRAVITINO_URI, GRAVITINO_USERNAME, GRAVITINO_PASSWORD, and GRAVITINO_METALAKE with your actual values.
5. Save and restart: Save the configuration and restart Windsurf.
6. Verify setup: Ensure the server is running and accessible via the configured endpoint.

Note: To secure API keys or sensitive credentials, use environment variables in the env section as shown above.

Claude

1. Ensure Node.js and uv are installed.
2. Edit the Claude configuration file.
3. Add the Gravitino MCP Server configuration (as above) to the mcpServers section.
4. Update environment variables for your deployment.
5. Save, restart Claude, and confirm the server is reachable.

Cursor

1. Prerequisites: Node.js and uv installed.
2. Open Cursor’s configuration.
3. Insert the Gravitino MCP Server JSON snippet (see above).
4. Fill in the correct environment variables.
5. Save, restart Cursor, and check connectivity.

Cline

1. Install Node.js and uv.
2. Go to your Cline config file.
3. Add the Gravitino MCP Server using the provided JSON structure.
4. Ensure all sensitive information is secured in the env section.
5. Save and restart Cline, then verify the MCP server connection.

Securing API Keys:
Use environment variables in the env object to store sensitive credentials such as tokens, usernames, and passwords.
Example:

"env": {
  "GRAVITINO_URI": "http://localhost:8090",
  "GRAVITINO_USERNAME": "admin",
  "GRAVITINO_PASSWORD": "admin"
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "Gravitino": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “Gravitino” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

| Roots Support | ⛔ | Not mentioned |

Based on the above tables, the Gravitino MCP server provides a minimal but functional integration, with clear setup instructions and tool exposure, but lacks prompt templates, resource definitions, and advanced MCP features such as roots or sampling.

Our opinion

While the Gravitino MCP server is easy to set up and exposes useful metadata tools, its documentation and server capabilities are limited in terms of MCP features like prompts, resources, and advanced agentic functions. It is suitable for basic metadata interaction but would benefit from more comprehensive MCP integration. MCP Score: 5/10

MCP Score