Mcp Server Unitycatalog: An Unity Catalog Mcp Server

What is MCP Server Unity Catalog?

The ### MCP Server Unity Catalog is a powerful server solution designed to manage and serve AI model context protocols. It provides a centralized platform for organizing, storing, and retrieving data related to AI models, ensuring that developers and data scientists can efficiently access the information they need to build and deploy AI applications.

Features of MCP Server Unity Catalog

• Centralized Data Management: The Unity Catalog allows users to manage all AI model data in one place, simplifying data retrieval and organization.
• Enhanced Collaboration: Multiple users can access and contribute to the catalog, fostering collaboration among teams working on AI projects.
• Version Control: The server supports versioning of AI models, enabling users to track changes and revert to previous versions if necessary.
• User-Friendly Interface: The intuitive interface makes it easy for users to navigate through the catalog and find the information they need quickly.
• Security and Compliance: The MCP Server ensures that all data is stored securely and complies with relevant data protection regulations.

How to Use MCP Server Unity Catalog

1. Installation: Begin by downloading the MCP Server Unity Catalog from the official repository. Follow the installation instructions provided in the documentation.
2. Configuration: After installation, configure the server settings to suit your project requirements. This includes setting up user permissions and data storage options.
3. Data Upload: Upload your AI model data to the catalog. You can organize the data into categories for easier access.
4. Accessing Data: Use the search functionality to quickly find specific models or datasets. The catalog allows filtering by various criteria to streamline the search process.
5. Collaboration: Invite team members to access the catalog and collaborate on projects. Utilize the version control feature to manage changes effectively.

Frequently Asked Questions

What types of data can be stored in the MCP Server Unity Catalog?

The catalog can store various types of data related to AI models, including model parameters, training datasets, evaluation metrics, and documentation.

Is the MCP Server Unity Catalog open-source?

Yes, the MCP Server Unity Catalog is an open-source project, allowing users to contribute to its development and customize it for their needs.

How do I contribute to the MCP Server Unity Catalog?

You can contribute by forking the repository, making your changes, and submitting a pull request. Ensure to follow the contribution guidelines outlined in the repository.

Can I integrate the MCP Server Unity Catalog with other tools?

Yes, the catalog is designed to be flexible and can be integrated with various data science and machine learning tools to enhance your workflow.

What support is available for users of the MCP Server Unity Catalog?

Users can access community support through forums and GitHub discussions. Additionally, documentation is provided to assist with setup and troubleshooting.

By leveraging the MCP Server Unity Catalog, teams can streamline their AI development processes, enhance collaboration, and ensure efficient data management.

mcp-server-unitycatalog: An Unity Catalog MCP server

<p align="center" float="left"> <img width="256" src="https://raw.githubusercontent.com/ognis1205/mcp-server-unitycatalog/main/docs/vscode1.webp" /> <img width="256" src="https://raw.githubusercontent.com/ognis1205/mcp-server-unitycatalog/main/docs/vscode2.webp" /> <img width="256" src="https://raw.githubusercontent.com/ognis1205/mcp-server-unitycatalog/main/docs/vscode3.webp" /> </p>

Overview

A Model Context Protocol server for Unity Catalog. This server provides Unity Catalog Functions as MCP tools.

Tools

You can use all Unity Catalog Functions registered in Unity Catalog alongside the following predefined Unity Catalog AI tools:

1. uc_list_functions

   • Lists functions within the specified parent catalog and schema.
   • Returns: A list of functions retrieved from Unity Catalog.

2. uc_get_function

   • Gets a function within a parent catalog and schema.
   • Input:
     • name (string): The name of the function (not fully-qualified).
   • Returns: A function details retrieved from Unity Catalog.

3. uc_create_function

   • Creates a function within a parent catalog and schema. WARNING: This API is experimental and will change in future versions.
   • Input:
     • name (string): The name of the function (not fully-qualified).
     • script (string): The Python script including the function to be registered.
   • Returns: A function details created within Unity Catalog.

4. uc_delete_function

   • Deletes a function within a parent catalog and schema.
   • Input:
     • name (string): The name of the function (not fully-qualified).
   • Returns: None.

Installation

Using uv

When using uv no specific installation is needed. We will use uvx to directly run mcp-server-git.

Configuration

These values can also be set via CLI options or .env environment variables. Required arguments are the Unity Catalog server, catalog, and schema, while the access token and verbosity level are optional. Run uv run mcp-server-unitycatalog --help for more detailed configuration options.

| Argument | Environment Variable | Description | Required/Optional | |-|-||-| | -u, --uc_server | UC_SERVER | The base URL of the Unity Catalog server. | Required | | -c, --uc_catalog | UC_CATALOG | The name of the Unity Catalog catalog. | Required | | -s, --uc_schema | UC_SCHEMA | The name of the schema within a Unity Catalog catalog. | Required | | -t, --uc_token | UC_TOKEN | The access token used to authorize API requests to the Unity Catalog server. | Optional | | -v, --uc_verbosity | UC_VERBOSITY | The verbosity level for logging. Default: warn. | Optional | | -l, --uc_log_directory | UC_LOG_DIRECTORY | The directory where log files will be stored. Default: .mcp_server_unitycatalog. | Optional |

Usage with Claude Desktop or VSCode Cline

Add this to your claude_desktop_config.json (or cline_mcp_settings.json):

<details> <summary>Using uv</summary>

{
  "mcpServers": {
    "unitycatalog": {
      "command": "uv",
      "args": [
        "--directory",
        "/<path to your local git repository>/mcp-server-unitycatalog",
        "run",
        "mcp-server-unitycatalog",
        "--uc_server",
        "<your unity catalog url>",
        "--uc_catalog",
        "<your catalog name>",
        "--uc_schema",
        "<your schema name>"
      ]
    }
  }
}

</details> <details> <summary>Using docker</summary>

• Note: replace '/Users/username' with the a path that you want to be accessible by this tool

{
  "mcpServers": {
    "unitycatalog": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "mcp/unitycatalog",
        "--uc_server",
        "<your unity catalog url>",
        "--uc_catalog",
        "<your catalog name>",
        "--uc_schema",
        "<your schema name>"
      ]
    }
  }
}

</details>

Building

Docker:

docker build -t mcp/unitycatalog .   

Future Plans

• Implement support for list_functions.
• Implement support for get_function.
• Implement support for create_python_function.
• Implement support for execute_function.
• Implement support for delete_function.
• Implement semantic catalog explorer tools.
• Add Docker image.
• Implement use_xxx methods. In the current implementation, catalog and schema need to be defined when starting the server. However, they will be implemented as use_catalog and use_schema functions, dynamically updating the list of available functions when the use_xxx is executed.

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.