> ## Documentation Index
> Fetch the complete documentation index at: https://deliveryhub.parametasolutions.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Documentation MCP Server

> Connect your AI tools to Parameta Delivery Hub documentation to discover datasets, retrieve connection details, and accelerate integration with WebSocket, Snowflake, SFTP, FIX, and more.

## About the Parameta Delivery Hub MCP

The Parameta Delivery Hub MCP (Model Context Protocol) provides a unified way for clients to **discover, access, and integrate with Parameta data delivery services** using AI-powered tools.

By connecting our MCP server to your preferred AI assistant (e.g. Claude, ChatGPT, VS Code), you can:

* Discover available Parameta delivery channels
* Retrieve corresponding connection and configuration details
* Generate integration examples (SQL queries, subscription messages, file formats)
* Troubleshoot connectivity or entitlement issues

The MCP connects your AI tools directly to Parameta Solutions Delivery Hub documentation, enabling **real-time, guided integration support** without manually searching documentation.

<Tip>
  Some AI tools like Claude support both MCP and skills. MCP gives access to your content, while skills instruct agents how to use that content effectively. They're complementary and connecting your MCP server gives agents access to both.
</Tip>

***

### Common Use Cases

<CardGroup cols={2}>
  <Card title="Snowflake Data Access" icon="database">
    * Discover available datasets and tables
    * Generate SQL queries for analysis
    * Export data into other tools and systems
  </Card>

  <Card title="WebSocket Streaming" icon="stream">
    * Retrieve endpoints and authentication methods
    * Generate subscription payloads
    * Stream data into real-time applications
  </Card>

  <Card title="SFTP Data Delivery" icon="folder">
    * Access file naming conventions and schedules
    * Retrieve sample file structures
    * Validate connectivity
  </Card>

  <Card title="Troubleshooting & Support" icon="hammer">
    * Diagnose connectivity issues
    * Identify missing entitlements
    * Provide configuration guidance
  </Card>
</CardGroup>

<Note>
  For detailed documentation on each delivery channel, see:

  * [Snowflake](https://docs.snowflake.com/en/user-guide/data-sharing-reader-create)
  * [WebSocket](/tabs/our-technologies/direct-delivery/real-time#websocket)
  * [SFTP](/tabs/our-technologies/direct-delivery/snap-files#parameta-sftp)
  * [FIX](/tabs/our-technologies/direct-delivery/real-time#fix-api-5-0-sp2)
</Note>

***

### How It Works

When connected, your AI assistant can securely query Parameta Solutions Delivery Hub documentation via a MCP server.

* The AI automatically retrieves relevant documentation when needed
* Responses are based on the latest available content
* You can ask questions in natural language

Example:

> "How do I access Parameta FX data in Snowflake?"

You do not need to manually search documentation, the MCP connection enables **context-aware, guided responses**.

***

## The MCP endpoint

Connect your AI tool to:

`https://deliveryhub.parametasolutions.com/authed/mcp`

<Note>
  The MCP returns the same documentation you see when logged in to this site — including
  record naming conventions, field groups and FID definitions, connection guides and data
  warehouse documentation — scoped to your entitlements.
</Note>

### Signing in

The first time your AI tool connects, it opens a browser window for you to sign in with
your usual Delivery Hub credentials. There is no API key or client secret to create or
store.

<Steps>
  <Step title="Your tool requests access">
    Your AI tool contacts the MCP endpoint and is told that sign-in is required.
  </Step>

  <Step title="You sign in">
    A browser window opens on the Delivery Hub sign-in page. Sign in as you normally
    would. If you already have an active session, this step completes automatically.
  </Step>

  <Step title="Your tool is authorised">
    Your tool receives an access token tied to your account and its entitlements. It
    refreshes automatically, so you only sign in once per tool.
  </Step>
</Steps>

<Note>
  Authentication methods may vary depending on the AI client you are using. Please follow
  the OAuth authentication flow supported by your chosen client, whether Kiro, Claude Code,
  Visual Studio Code, Cursor, or another MCP-compatible application.
</Note>

<Tip>
  Your entitlements are applied on every request. If your access changes, the
  documentation available through the MCP changes with it — no reconfiguration needed.
</Tip>

## Connect to the Parameta Delivery Hub MCP

Here's a few ways in which you can connect to our MCP server to your preferred AI tools.

<Tabs>
  <Tab title="VS Code">
    <Steps>
      <Step title="Get our MCP server URL">
        This is: `https://deliveryhub.parametasolutions.com/authed/mcp`
      </Step>

      <Step title="Create your VS Code configuration">
        1. Create a `.vscode/mcp.json` file.
        2. In `mcp.json`, configure your server:

        ```json theme={"theme":{"light":"github-light","dark":"github-dark"}}
        {
          "servers": {
            "parameta-solutions-documentation": {
              "type": "http",
              "url": "https://deliveryhub.parametasolutions.com/authed/mcp"
            }
          }
        }
        ```
      </Step>
    </Steps>

    See the [VS Code documentation](https://code.visualstudio.com/docs/copilot/chat/mcp-servers) for more details.
  </Tab>

  <Tab title="Cursor">
    <Steps>
      <Step title="Get our MCP server URL">
        Ours is: `https://deliveryhub.parametasolutions.com/authed/mcp`
      </Step>

      <Step title="Create your MCP server confiugration.">
        1. Use <kbd>Command</kbd> + <kbd>Shift</kbd> + <kbd>P</kbd> (<kbd>Ctrl</kbd> + <kbd>Shift</kbd> + <kbd>P</kbd> on Windows) to open the command palette.
        2. Search for `Open MCP settings`.
        3. Click **Add custom MCP**. This opens the `mcp.json` file.
        4. In `mcp.json`, configure your server:

        ```json theme={"theme":{"light":"github-light","dark":"github-dark"}}
        {
          "mcpServers": {
            "parameta-solutions-documentation": {
              "url": "https://deliveryhub.parametasolutions.com/authed/mcp"
            }
          }
        }
        ```
      </Step>
    </Steps>
  </Tab>

  <Tab title="Claude">
    To use the Mintlify MCP server with Claude:

    <Steps>
      <Step title="Add the Mintlify MCP server to Claude">
        1. Navigate to the [Connectors](https://claude.ai/settings/connectors) page in the Claude settings.
        2. Click **Add custom connector**.
        3. Add the MCP server:

        * Name: `Parameta Solutions Documentation`
        * URL: `https://deliveryhub.parametasolutions.com/authed/mcp`

        4. Click **Add**.
      </Step>

      <Step title="Access the MCP server in your chat">
        1. When using Claude, click the attachments button (the plus icon).
        2. Select the Mintlify MCP server.
        3. Ask Claude a question about our documentation.
      </Step>
    </Steps>

    See the [Model Context Protocol documentation](https://modelcontextprotocol.io/docs/tutorials/use-remote-mcp-server#connecting-to-a-remote-mcp-server) for more details.
  </Tab>

  <Tab title="Claude Code">
    To use the Mintlify MCP server with Claude Code, run the following command:

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    claude mcp add --scope user --transport http parameta-delivery-hub https://deliveryhub.parametasolutions.com/authed/mcp
    ```

    Then sign in by running `/mcp` inside an interactive `claude` session and
    selecting **parameta-delivery-hub**. A browser window opens for you to sign in.

    Test the connection by running:

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    claude mcp list
    ```

    It should report `parameta-delivery-hub` as connected once you have signed in.

    See the [Claude Code documentation](https://docs.anthropic.com/en/docs/claude-code/mcp#installing-mcp-servers) for more details.
  </Tab>

  <Tab title="Kiro CLI">
    Add our MCP server to your Kiro CLI using:

    ```shellscript theme={"theme":{"light":"github-light","dark":"github-dark"}}
    kiro-cli mcp add --name parametadeliveryhub --url https://deliveryhub.parametasolutions.com/authed/mcp
    ```
  </Tab>
</Tabs>

### Authentication & Entitlements

The MCP server provides guidance and documentation—it does not grant data access directly.
Signing in controls which **documentation** your AI tool can read; it does not by itself
grant access to market data.

To access Parameta Solutions data, you must have:

* Active commercial agreement
* Valid credentials (API keys, Snowflake access, etc.)
* Correct entitlements for specific datasets

<Note>
  **Seeing less documentation than you expect?** Confirm you completed sign-in. If you
  are signed in and a page you need is still unavailable, your account may not be entitled
  to it — contact your Parameta Solutions representative.
</Note>

If you are unable to access data, contact your Parameta Solutions representative.