A governed MCP server, which is a boring way of saying nobody gets a shared login
MCP for your data warehouse: Claude, Cursor, Codex, ChatGPT and your own agents query Snowflake, BigQuery, Databricks and more through Rig, each with a role, certified metrics and a log of every query
Each person signs in as themselves. Each agent gets a copy of a role you trust.
Agents connect with their own token and a daily call cap, and cannot sign in to Rig.
Roles set the schemas, columns and rows a caller can read, with PII masked.
Every call is logged under the caller's name, including refused calls.
MCP on the warehouse you already run
Each warehouse vendor now ships an MCP server of its own. These pages describe each one from the vendor's documentation and show where Rig's Gateway fits.
Gateway decides who and which agents can query what. Rig Map gives every tool the same certified metrics and table meanings. For the step-by-step version, read how to connect AI agents to your data warehouse. Building it yourself in Claude Code? Read Rig compared with Claude Code.
See Rig MCP in action
Watch an AI coding agent discover tables, resolve joins, and query a warehouse, all through Rig MCP.
One context layer, every AI tool
Any tool that supports MCP can discover your tables, understand your schema, and query your warehouse, without ever seeing raw credentials.
How Rig MCP works
"Find tables related to subscription revenue and show me the join path to users"
Schemas, column descriptions, join keys & sample data
Governed, read-only, auto-limited, and no raw warehouse credentials ever leave Rig
Built for safe, governed access
OAuth
Every user's data access is managed via OAuth. Set and audit permissions and logs per user and per team.
Pre-computed context
Metadata, embeddings, join graphs, and sample values served from an in-process database, with no runtime LLM calls for search.
Sandbox-first SQL
All agent queries validated in a sandbox. Execution auto-limits and respects permissions.
Common questions
Certify the metrics once in Rig Map, then connect Claude or Cursor to Rig’s MCP server. A person signs in with OAuth and gets their own role. An agent gets its own role and token. Either way, the tool looks up the certified metric before it writes SQL, sees only the schemas, columns and rows the role allows, and every call lands in the audit log.
MCP (Model Context Protocol) is an open protocol that lets an AI tool discover and call tools on a server. An MCP server for a data warehouse lets Claude, Cursor or your own agent find tables, read their meaning and run SQL. Rig's server puts Gateway in front of the warehouse, so every caller has a role and every query is logged.
An MCP (Model Context Protocol) server that gives AI tools, like Codex, Claude Code, Cursor, ChatGPT, and Claude Cowork, governed access to your warehouse: schemas, metrics, joins, and live data through one protocol, without ever exposing raw database credentials.
Any tool that supports the Model Context Protocol. Rig exposes 17 MCP tools for semantic table search, join and lineage resolution, and sandboxed querying, so the agent gets exactly the context it needs and nothing more.
Role-based access control is enforced on every query, all SQL is validated in a sandbox in under 10ms and auto-limited, access is managed via OAuth, and raw credentials never leave Rig. Every request is permissioned and logged for audit.
It adds less load than pointing an agent at the warehouse directly. Context such as metadata, embeddings, join graphs and sample values is pre-computed and served from an in-process database, so an agent looks tables up without querying the warehouse, and each agent has a daily call cap.