Model Context Protocol (MCP)
Connect compatible AI agents and clients to your governed Stackless workspace.
Stackless provides a hosted Model Context Protocol (MCP) server for exploring and operating the data assets available to your Stackless account. The server uses your existing Stackless identity and permissions; connecting an AI client does not grant additional access.
Before you connect
You need:
- An active Stackless account.
- The hostname of your Stackless workspace, such as
https://your-workspace.stacklessdata.com. - An MCP client that supports remote Streamable HTTP servers and OAuth 2.0.
Your MCP endpoint is:
https://your-workspace.stacklessdata.com/api/v1/mcp/transport
Replace your-workspace with the hostname supplied by your Stackless
administrator. Do not paste access tokens, session cookies, or other secrets
into the connector URL.
What the connector can do
The tools available to you depend on your Stackless role and workspace configuration. Typical uses include:
- Finding relevant data assets and explaining their columns.
- Inspecting lineage, freshness, and recent data runs.
- Querying governed warehouse data through Stackless guardrails.
- Drafting transformations, semantic models, and dashboards.
- Previewing and publishing reviewed changes when your role permits it.
Try prompts such as:
- “Find the data assets related to revenue and explain which one I should use.”
- “Trace the lineage of this dashboard and identify its upstream models.”
- “Show the status of recent Stackless runs and explain any failures.”
Next steps
- Connect an AI agent or client.
- Review permissions and security.
- Use the troubleshooting guide if a connection or tool call fails.