Models you choose
Enable AI access for specific models. Share them with individual users or workspace groups.
Access verified before every queryRENTA CONTEXT LAYER
Give AI the context
behind your data.
Turn your warehouse models into data your AI assistant can work with. Define measures, explain your business logic, and ask questions through Renta MCP.
Built for Google BigQuery and ClickHouse.
Claudewith Renta MCPInteractive demoYou
Which channels brought in the most revenue last month?
Checking the orders model and querying revenue…Works with your AI toolsClaude Code
CodexClaude Desktop
Cursor
Antigravity CLI
Claude CodeCodexClaude DesktopCursorFROM BUSINESS QUESTION TO WAREHOUSE ANSWER
A question in your words.
An answer from your models.
Give your assistant the definitions it needs to choose the right model, fields, and calculations.
CONTEXT USED FOR THIS QUESTION
orders
ordersOne row per completed order. Revenue is in USD, excluding VAT. Test orders are excluded in the model.
- Measure
revenue_sum- Dimension
channel- Time range
- Last month
AI assistant with Renta MCPIllustrative analysisWhich channels brought in the most revenue last month?
✓ Query result
Paid search leads with $48,200, followed by organic search at $31,600.
Revenue · USD
Paid search$48,200
Organic search$31,600
Email$18,400
DEFINED BY YOUR TEAM. AVAILABLE TO AI.
Your business logic,
built into every model.
Choose how your data can be calculated.
Enable the aggregations that make sense for each column. Your assistant discovers those measures before building a query.
Explore model setupQuerySchema & keyAccess
Measures
Choose which aggregations each column exposes to AI agents and the Renta API.
| Column | SUM | AVG | MIN | MAX | MEDIAN | P95 | COUNT | DISTINCT |
|---|---|---|---|---|---|---|---|---|
| order_idTEXT | ||||||||
| countryTEXT | ||||||||
| revenueFLOAT | ||||||||
| itemsINT |
Revenue measures available to AI
revenue_sumrevenue_avgA SHARED FOUNDATION
Keep your data where it is.
Bring its meaning to AI.
Start with the tables and SQL you already use. Renta connects your model definitions to the tools your team works in.
01 / YOUR WAREHOUSEGoogle BigQuery
ClickHouse
Google BigQueryClickHouseChoose a table or SQL model.
02 / YOUR CONTEXT
Renta Context LayerDefinitions · Measures · Access
Renta Context LayerDefinitions · Measures · AccessDefine what the data means.
03 / YOUR AI TOOLSClaude CodeCodex + more via MCP
Claude CodeCodex + more via MCPAsk questions using your models.
THE RIGHT DATA. THE RIGHT PEOPLE.You decide who
You decide who
gets the answers.
Give people access to the models they need. Their AI assistant works within those same boundaries.
Share with individual users or a whole team. Workspace owners always retain access.
QuerySchema & keyMeasuresMetadata & AIAccess
Access
Choose who can describe and query this model.
Users
Workspace members with direct access.
| User | Role | Access |
|---|---|---|
Alex Morganalex@example.com | Owner | Always |
Sam Leesam@example.com | Member | Direct |
Groups
Access for everyone in the group.
| Group | Members |
|---|---|
MarketingCampaigns & acquisition | 6 |
BUILT AROUND YOUR DATA SECURITY
Security first.
Your data stays in your warehouse.
Renta Context Layer connects your AI assistant to your warehouse without storing a copy of your warehouse data. Queries run in your warehouse; results pass through Renta to your assistant.
Read-only queries
Context Layer queries and field sampling read from your warehouse without changing its records.
Query through your model definitionsBounded execution
Query timeouts and per-query data limits constrain execution. Results include query statistics for inspection.
Read about query limitsWhat is Renta Context Layer?
Context Layer makes your Renta data models available to AI assistants. It exposes model descriptions, dimensions, and configured measures through MCP. The assistant selects the fields and filters it needs; Renta builds and runs the SQL against your warehouse.
Which data warehouses does it support?
Context Layer supports Google BigQuery and ClickHouse. Start with a table or a SQL model connected to one of these warehouses.
Do I need to write SQL?
You can start with an existing table and configure measures and descriptions in the Renta interface. Use a SQL model when you need joins, exclusions, or other business logic. Each Context Layer query uses one model; combine tables in the model's SQL first.
Which AI clients can I connect?
Use Renta MCP with Claude Code, Codex, Claude Desktop, Cursor, or Antigravity CLI. You can also build a custom integration with the Context Layer REST API. The Connect MCP button provides setup prompts for supported clients.
How is access controlled?
A model must have an AI-enabled scope and be accessible to the authenticated user. Renta checks workspace membership and model access on each request. Grant access to individual users or workspace groups; workspace owners always have access.
Can Context Layer change warehouse data?
The Context Layer discovery, field sampling, and query actions read data; they do not modify warehouse records. Other Renta MCP tools can manage resources and pipelines separately.
Can I use the same model for Reverse ETL?
Yes. Choose the AI agents & Reverse ETL scope to use a model in both workflows. AI can query its configured dimensions and measures, while a Reverse ETL pipeline syncs its rows to a supported destination.
Your business has context.
Give it to your AI.
Give it to your AI.
Start with one model. Connect the assistant you already use.
Free for 7 days. No credit card required