MCP Server with Datasaur Sandbox

by ansemin

280 downloads
Not rated
GitHub

Description

# MCP Server with Datasaur Sandbox A comprehensive guide for beginners to set up and use a Model Context Protocol (MCP) server with Datasaur Sandbox. ## Table of Contents - [Introduction](#introduction) - [Prerequisites](#prerequisites) - [Installation](#installation) -…

About

# MCP Server with Datasaur Sandbox A comprehensive guide for beginners to set up and use a Model Context Protocol (MCP) server with Datasaur Sandbox. ## Table of Contents - [Introduction](#introduction) - [Prerequisites](#prerequisites) - [Installation](#installation) - [Configuration](#configuration) - [Running Your…

Details

Author
ansemin
Downloads
280
Categories
Other

- Bridges applications with Datasaur’s managed AI model APIs
- Provides data processing tools (e.g., CSV to JSON conversion)
- Enables prompting any AI model deployed in Datasaur
- Supports creation of helper tools for common tasks
- Includes troubleshooting guidance and extension patterns

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name MCP Server with Datasaur Sandbox
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install Python 3.8+, clone the project, create a virtual environment, install dependencies (mcp[cli], httpx, python‑dotenv, uv), create a .env file with DATASAUR_API_KEY and DATASAUR_SANDBOX_API_URL, and then run python main.py. For Claude Desktop, configure claude_desktop_config.json with the server command and environment variables.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcp server with datasaur sandbox": {
            "MCP-Server---Datasaur": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

McpServers

{
    "MCP-Server---Datasaur": {
        "command": "python",
        "args": [
            "-m",
            "venv",
            "venv"
        ]
    }
}

MCP Server with Datasaur Sandbox

A comprehensive guide for beginners to set up and use a Model Context Protocol (MCP) server with Datasaur Sandbox.

Table of Contents

- Introduction - Prerequisites - Installation - Configuration - Running Your MCP Server - Using Your MCP Server - Troubleshooting - Extending Functionality

Introduction

What is MCP?

Model Context Protocol (MCP) is a standardized way for applications to communicate with AI models. It defines a protocol that allows tools to exchange structured data with large language models (LLMs), enabling them to use external functions and tools.

What is a Datasaur Sandbox?

Datasaur Sandbox provides managed API access to various AI models. This project implements an MCP server that acts as a bridge between your applications and Datasaur's API endpoints, allowing your applications to:

- Process and analyze data
- Access AI models deployed through Datasaur
- Build specialized assistants for various tasks

Prerequisites

Before you begin, ensure you have:

1. Python 3.8+ installed on your system
- Download from python.org
- Make sure to check "Add Python to PATH" during installation

2. A Datasaur account with API access
- Sign up at datasaur.ai
- Obtain your API key from your account dashboard

3. Basic knowledge of command-line operations

Installation

Step 1: Clone or Create the Project

Create a new directory for your project:

mkdir datasaur-mcp-server
cd datasaur-mcp-server

Step 2: Set Up Your Environment

Create a virtual environment (recommended):

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.