Self-service MCP setup

Connect your own warehouse to your agent over MCP — read-only, running locally, never touching Nodal.

The interview verifies definitions against your live warehouse, and the context repo it generates queries that warehouse to answer questions. Both need read-only access to your data — so you connect your warehouse to your agent over MCP, using the official MCP server for your warehouse.

This runs entirely in your own agent. Nodal is not in this loop and never sees your database. You wire a warehouse MCP server directly into your agent (Claude Code, Codex, Cursor, …); the credentials stay with you.

Pick your warehouse’s MCP server

These are maintained by the warehouse vendors and the MCP community — Nodal just points you to them.

Warehouse	MCP server
Snowflake	Snowflake MCP
BigQuery	MCP Toolbox for Databases (Google)
Redshift	AWS Labs MCP servers (Redshift)
Databricks	Databricks MCP
Other / general	Model Context Protocol servers

Use a read-only role

Give the MCP server a read-only role or credential. The interview and the generated data-question skill only ever run SELECT. A read-only role is the simplest way to guarantee that.

Wire it into your agent

Follow your agent’s MCP documentation to add the server. For Claude Code, for example:

claude mcp add <name> -- <command to launch your warehouse MCP server>

Once your warehouse is connected, you’re ready to build context.

Build your context

Run the interview against your connected warehouse.

Share with your team

When you’re ready to serve context to everyone, move to the hosted Nodal MCP.