Palantir Foundry

🚀 Foundry MCP Server

A Model Context Protocol (MCP) server for interacting with Foundry. It enables AI assistants to interact with datasets, ontology objects, and functions.

✨ Features

• List datasets
• Query datasets
• List ontology objects
• Query ontology objects
• List functions
• Execute functions

📦 Installation

Prerequisites

• Python 3.9+
• mcp
• pyarrow
• pandas
• foundry-platform-sdk

🌍 Environment Variables

The server requires several configuration variables to run:

• If no token is provided, the server will attempt to authenticate via the OAuth2 flow using the client ID and client secret.

💻 Usage Examples

Basic Usage

First, clone the repository and add the configuration to your application:

{
  "mcpServers": {
    "foundry": {
      "command": "uv",
      "args": [
        "--directory", 
        "<Path to mcp_server>",
        "run",
        "mcp-server-foundry"
      ],
      "env": {
        "HOSTNAME": "<Hostname>",
        "TOKEN": "<Token>",
        "CLIENT_ID": "<Client ID>",
        "CLIENT_SECRET": "<Client Secret>",
        "SCOPES": "<Scopes>",
        "ONTOLOGY_ID": "<Ontology ID>"
      }
    }
  }
}

Advanced Usage

Run the server in development mode:

# Clone the repository
git clone git@github.com:qwert666/mcp-server-foundry.git

# Run the server
npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-foundry-server run mcp-server-foundry

🤝 Contribution Guidelines

• Fork the repository.
• Create a feature branch (git checkout -b feature/amazing-feature).
• Commit your changes (git commit -m 'Add some amazing feature').
• Push to the branch (git push origin feature/amazing-feature).
• Open a Pull Request.

📄 License

This project is under the MIT License - see the LICENSE file for details.