For the complete documentation index, see llms.txt. This page is also available as Markdown.

Custom

Connect any agentic framework to Data Product MCP with the generic configuration.

Connect any agentic framework to Data Product MCP using streamable HTTP.

Prerequisites

Your DataOS instance URL, a DataOS API token, and a framework that can connect to MCP tools over streamable HTTP. See API tokens for how tokens work.

Connect

Configure your framework with these values, replacing <API_TOKEN>:

Field
Value

Server name

DataProduct-MCP

Transport

Streamable HTTP

URL

https://<instance-url>/dataproduct-mcp/api/v1

Header key

apikey

Header value

<API_TOKEN>

You can copy these from Home → Connect to Data Product MCP in DataOS. Most MCP client libraries accept a server definition shaped like this:

{
  "DataProduct-MCP": {
    "transport": "http",
    "url": "https://<instance-url>/dataproduct-mcp/api/v1",
    "headers": { "apikey": "<API_TOKEN>" }
  }
}

Adapt the syntax to your framework's MCP adapter. For framework-specific examples, see LangChain or Vercel AI SDK.

Verify

List the available tools from DataProduct-MCP, then ask the agent What data products am I authorized to access?. A working connection returns products scoped to your token and permissions.

Last updated

Was this helpful?