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

    Role

    Each person signs in as themselves. Each agent gets a copy of a role you trust.

    Token

    Agents connect with their own token and a daily call cap, and cannot sign in to Rig.

    Row limits

    Roles set the schemas, columns and rows a caller can read, with PII masked.

    Query log

    Every call is logged under the caller's name, including refused calls.

    Cursor"write a new dbt model"Claude Code"add data to slides"ChatGPT"what drove churn last month?"Rig MCPContext Layersearch_tablesget_join_pathtest_sqlexecute_sqlget_table_columnsAI TOOLSMCP TOOL 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.

    Claude Code
    CLI agent for software engineering
    Cursor
    AI-native code editor
    ChatGPT
    Conversational AI assistant
    Claude Cowork
    Collaborative AI workspace
    Any MCP client
    Open standard, supported by Claude, Cursor and ChatGPT

    How Rig MCP works

    // AI tool request

    "Find tables related to subscription revenue and show me the join path to users"

    search_tables
    get_join_path
    // Rig MCP server
    Semantic search across 2,900+ tables
    Resolve joins, lineage & sample values
    RBAC permissions enforced per-query
    Return only relevant context to the agent
    // Returned to agent

    Schemas, column descriptions, join keys & sample data

    Governed, read-only, auto-limited, and no raw warehouse credentials ever leave Rig

    17
    Rig MCP tools available
    <10ms
    Sandbox SQL validation

    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.

    Give every AI tool a role and a log