> ## Documentation Index
> Fetch the complete documentation index at: https://docs.quantspace.limex.pro/llms.txt
> Use this file to discover all available pages before exploring further.

# QuantX Quickstart

> Connect to a hosted MCP server and run the first tool call

## 1. Pick the Server

Use the [MCP Server Catalog](/quantx/servers/deployed) to choose the server for the workflow.

| Goal                            | Start here                                                                    |
| ------------------------------- | ----------------------------------------------------------------------------- |
| Load OHLCV data or indicators   | [Dataloader Server](/quantx/servers/dataloader)                               |
| Compute volatility estimates    | [Volatility Scaling Lab Server](/quantx/servers/volatility-scaling-lab)       |
| Fit statistical factor models   | [Statistical Factor Models Server](/quantx/servers/statistical-factor-models) |
| Fit regime-switching JumpModels | [Jump Models Server](/quantx/servers/jump-models)                             |
| Generate ExtremeHurst signals   | [Parallax ExtremeHurst Server](/quantx/servers/parallax-extreme-hurst)        |

## 2. Add It to Your Client

<Tabs>
  <Tab title="Cursor">
    ```json theme={null}
    {
      "mcpServers": {
        "volatility-scaling-lab": {
          "url": "https://volatility-scaling-lab-production.up.railway.app/mcp/qca-open-loop-volatility"
        }
      }
    }
    ```
  </Tab>

  <Tab title="Bearer auth">
    ```json theme={null}
    {
      "mcpServers": {
        "volatility-scaling-lab": {
          "url": "https://volatility-scaling-lab-production.up.railway.app/mcp/qca-open-loop-volatility",
          "headers": {
            "Authorization": "Bearer ${env:VOLSCALE_MCP_TOKEN}"
          }
        }
      }
    }
    ```
  </Tab>
</Tabs>

See [MCP Client Setup](/quantx/servers/deployed/client-setup) for all servers and generic HTTP examples.

## 3. Run a Small Tool Call

Ask your MCP client to call `compute-ewma-volatility-series` with this payload:

```json theme={null}
{
  "request": {
    "ticker": "SPY",
    "start_date": "2020-01-01",
    "halflife": 252,
    "annualize": true
  }
}
```

## 4. Handle Large Outputs

If a tool returns a `result_id`, use the result/artifact helpers documented in [Shared MCP Tools](/quantx/servers/deployed/shared-tools). The usual path is preview, fetch if needed, then save as an artifact when the output should be downloaded.

## 5. Next Steps

<CardGroup cols={2}>
  <Card title="Browse servers" icon="server" href="/quantx/servers/deployed">
    Compare all MCP endpoints and choose the right one for each workflow.
  </Card>

  <Card title="Client setup" icon="plug" href="/quantx/servers/deployed/client-setup">
    Configure Cursor, Claude Desktop, and generic streamable HTTP clients.
  </Card>
</CardGroup>