Documentation

Learn how to use our scientific tools, and how the results are calculated

Get Started
A line drawing of a laptop. Generated by AI

Endpoints

For Data Scientists

Tutorials

Try it out

Get a Key

If you are using an MCP Client to connect an AI Agent, follow the instructions for your platform below:

Add this to your claude_desktop_config.json file:

{
  "mcpServers": {
    "scientific-microservices": {
      "type": "streamable-http",
      "url": "https://mcp.scientificmicroservices.com/mcp",
      "requestOptions": {
        "headers": {
          "email": "YOUR_EMAIL",
          "key": "YOUR_KEY"
        }
      }
    }
  }
}

Add this under Cursor Settings > Features > MCP or in your .cursor/mcp.json:

{
  "mcpServers": {
    "Scientific Microservices": {
      "type": "sse",
      "url": "https://mcp.scientificmicroservices.com/mcp",
      "headers": {
        "email": "YOUR_EMAIL",
        "key": "YOUR_KEY"
      }
    }
  }
}

Add this to your VS Code settings.json under the MCP extensions block:

"github.copilot.mcp.servers": [
  {
    "name": "Scientific Microservices",
    "type": "streamable-http",
    "url": "https://mcp.scientificmicroservices.com/mcp",
    "requestOptions": {
      "headers": {
        "email": "YOUR_EMAIL",
        "key": "YOUR_KEY"
      }
    }
  }
]

Configure your Agent One environment variables or integration YAML:

mcpServers:
  - name: Scientific Microservices
    type: streamable-http
    url: https://mcp.scientificmicroservices.com/mcp
    requestOptions:
      headers:
        email: ${YOUR_EMAIL}
        key: ${YOUR_KEY}

Configure this in your AgentForce Action settings (JSON format):

{
  "serverName": "Scientific Microservices",
  "protocol": "streamable-http",
  "endpoint": "https://mcp.scientificmicroservices.com/mcp",
  "authentication": {
    "type": "customHeaders",
    "headers": {
      "email": "YOUR_EMAIL",
      "key": "YOUR_KEY"
    }
  }
}

Paste this YAML into your ChatMCP connections configuration:

mcpServers:
  - name: Scientific Microservices
    type: streamable-http
    url: https://mcp.scientificmicroservices.com/mcp
    requestOptions:
      headers:
        email: YOUR_EMAIL
        key: YOUR_KEY

Define the MCP tool endpoint in your Vertex AI Agent Builder configuration:

{
  "tools": [
    {
      "mcp": {
        "serverName": "Scientific Microservices",
        "type": "streamable-http",
        "url": "https://mcp.scientificmicroservices.com/mcp",
        "httpHeaders": {
          "email": "YOUR_EMAIL",
          "key": "YOUR_KEY"
        }
      }
    }
  ]
}

For developers building smart ETL workflows, you can run a test request with curl:

curl --request POST \
  --url 'https://api.scientificmicroservices.com/detectoutliers' \
  --header 'Content-Type: application/json' \
  --header 'email:YOUR_EMAIL' \
  --header 'key:YOUR_KEY' \
  --data '[10.1727,11.9026,7.9209,9.0841,9.8298,11.345,9.6483,8.9257,8.9788,958.9969,11.1933,12.1186,9.5798,10.0861,10.1675,10.2935,11.2547,10.4636,9.6607,9.7316]'

[{"position":9,"value":958.9969}]