Palantir Foundry MCP server

The Foundry MCP Server is an implementation of the Model Context Protocol that enables AI assistants to interact with Foundry data systems. It provides capabilities for querying datasets, working with ontology objects, and executing functions within the Foundry platform.

Prerequisites

To use the Foundry MCP Server, you'll need:

• Python 3.9 or higher
• Required packages:
  • mcp
  • pyarrow
  • pandas
  • foundry-platform-sdk

Configuration

The server requires several environment variables to connect to your Foundry instance:

** If a token is not provided, the server will authenticate using OAuth2 flow with client_id and client_secret

Installation and Setup

To install and run the MCP server with the uv package manager:

1. Clone the repository
2. Configure your application with the required environment variables

Here's an example configuration:

{
  "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>"
      }
    }
  }
}

Running the Server

To run the server with the MCP inspector tool:

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

Available Tools

The Foundry MCP Server provides several tools for AI assistants to work with Foundry data:

• List datasets: View available datasets in your Foundry instance
• Query datasets: Retrieve and analyze data from specific datasets
• List ontology objects: Browse the available ontology objects
• Query ontology objects: Retrieve and work with specific ontology objects
• List functions: View available functions that can be executed
• Execute functions: Run specific functions to perform operations within Foundry

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.