---
title: "Data context and governance: Rig Map, Gateway and ingestion | Rig"
description: "Rig Map describes your warehouse, Gateway decides who and which agents can query it, and Ingest brings the data in, with guides to MCP and semantic layers."
canonical: "https://rig.so/use-cases/data-context-and-governance"
format: markdown
---

Data context and governance

# A map of your warehouse, and a way to decide who can query it

Data context tells people and AI agents what your warehouse holds and what it means. Governance decides who can query it and records what they did. Rig does both on the warehouse you already run: Rig Map holds the context, Gateway enforces access, and Ingest brings in the data when you need it.

[Book a call with an architect](https://rig.so/book-demo)

Your systems, in viewShared data and definitions

**Salesforce**Customers & revenue

N

**NetSuite**Finance & orders

S

**Shopify**Commerce

❄

**Snowflake**Your warehouse

Systems Map

Context & definitions

ReportsWorkflowsAgents

Dependencies for one field

The reports, flows and teams that use it.

Impact mapped

Illustrative platform viewIngest → Rig Map → Migrate → Run

## Agents query the warehouse with a shared login and a prompt file

Teams usually hand Claude or Cursor a service account, then write a prompt file to explain the tables. The agent can see everything, the prompt file drifts from the schema within weeks, and nobody can say which agent ran which query.

## Where each part fits

- A prompt file about the tables
  
  ### Rig Map
  
  Rig Map holds the ontology, the semantic layer and the context layer, drafted from the warehouse and kept current as schemas change.
- A shared warehouse login
  
  ### Gateway
  
  Each person and each agent gets a role, agents get a token and a daily call limit, and every query is logged by name.
- An MCP server per tool
  
  ### One MCP connection
  
  Claude, Cursor, ChatGPT and your own agents connect to Rig over MCP, with the same rules in each.
- Metrics inside the BI tool
  
  ### A semantic layer in the warehouse
  
  Certified metrics are defined once in your warehouse, for BI tools and AI agents alike.
- A per-row pipeline bill
  
  ### Ingest
  
  Ingest syncs 30+ tools on a schedule. It is priced on the compute that runs your syncs, with no per-row or per-connector charge, and you can keep any pipeline that already works.
- A lineage diagram drawn once and left
  
  ### Lineage you can check
  
  The Systems Map follows a field from the source system to the reports, workflows and agents that read it.

## How the work runs

1. ### Bring the data in
   
   Ingest syncs your tools into your warehouse on a schedule, or Rig works on the pipelines you already have.
2. ### Map it
   
   Rig Map drafts table descriptions, joins and metrics from the warehouse, and your data owners certify them.
3. ### Decide who can query it
   
   Gateway gives each person and each agent a role, with schema, column and row rules, and gives agents a token and a daily call limit.
4. ### Connect the tools
   
   Claude, Cursor, ChatGPT and your own agents connect over MCP, read the certified definitions first, and every call is logged.

Customer story / Cleo

8,023

requests from one analyst’s agents in 30 days

98%

success rate

One Cleo Growth Specialist’s agents made 8,023 requests to company data in 30 days, on the certified metrics Cleo’s data team reviews.

[Read the story](https://rig.so/case-studies/cleo)

## Pages in data context and governance

[Rig Map](https://rig.so/products/rig-map)[Gateway](https://rig.so/products/gateway)[Ingest](https://rig.so/products/ingest)[MCP for your data warehouse](https://rig.so/uses/mcp)[Snowflake MCP](https://rig.so/mcp/snowflake)[Databricks MCP](https://rig.so/mcp/databricks)[BigQuery MCP](https://rig.so/mcp/bigquery)[Salesforce MCP](https://rig.so/mcp/salesforce)[Snowflake semantic views](https://rig.so/semantic-layer/snowflake)[Semantic layer alternatives](https://rig.so/compare/semantic-layer)[Company brain](https://rig.so/use-cases/company-brain)[Agent data governance](https://rig.so/use-cases/agent-data-governance)[Data governance for AI](https://rig.so/data-governance-for-ai)[Managed data stack](https://rig.so/use-cases/managed-data-stack)[Fivetran migration](https://rig.so/use-cases/pipeline-migration)[Fivetran alternatives](https://rig.so/compare/fivetran-alternatives)[Fivetran cost calculator](https://rig.so/tools/fivetran-cost-calculator)[Glossary](https://rig.so/glossary)[Blog](https://rig.so/blog)

## Read the explainers

[What is a semantic layer?](https://rig.so/blog/wtf-is-a-semantic-layer)[What actually is context?](https://rig.so/blog/what-actually-is-context)[How to connect AI agents to your warehouse](https://rig.so/blog/how-to-connect-ai-agents-to-your-data-warehouse)

## Common questions

What is data context and governance?

Data context is what people and agents need to know about the warehouse: what each table means, how tables join and which metrics are certified. Governance decides who may query what and records what happened. Rig Map handles the context and Gateway handles the governance.

How do a context layer and a gateway work together?

The agent reads the context layer to pick the right table and metric. The gateway checks the agent’s role, applies row and column rules, counts the call against its limit and logs the query.

Do we need Ingest?

No. Rig Map and Gateway work on the warehouse and pipelines you already run, and Ingest is optional.

Which warehouses does this work on?

It works on Snowflake, BigQuery, Databricks, Redshift, Postgres and the other warehouses Rig connects to, or a warehouse Rig hosts for you.

How do I expose governed business metrics to Claude and Cursor?

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.

SOC 2 Type 2EU and US hostingRole-based accessYour warehouse or ours

Talk to Rig

## What work do you want to improve?

Tell us where your team spends time, loses money or needs better information.
In a 30-minute call, we’ll discuss the data and systems work that could help.

[Book a call with an architect](https://rig.so/book-demo)Use the platform with your team, or add our engineers.

---

- [This page as HTML](https://rig.so/use-cases/data-context-and-governance)
- [Site map for language models](https://rig.so/llms.txt)
- [API and agent documentation](https://rig.so/developers)
