Skip to main content

​
How agents access your data

Your AI agents connect to your app’s data through an MCP Server (Model Context Protocol). This gives agents flexible, powerful access to read, update, and insert data — no endpoint configuration or function definitions needed.
The MCP Server is how agents interact with your app’s live data. Without it, an agent can only chat and reference knowledge base documents. With MCP data access, it can answer questions like “Show me all deals closing this month” by querying your data directly.

​
How it works

1

Build your app with data models

Create your application with the data models and features you need.
2

Create an agent

Describe the assistant you want and what data it should access.
3

Agent gets automatic data access

The MCP Server automatically connects your agent to your app’s data. No manual configuration needed.
4

Optionally restrict with scopes

By default, agents can access all your app’s collections. Add scopes to restrict access to specific collections when needed.
Agents can also access data synced from external sources via datasets. Add sources like HubSpot or Google Sheets to a dataset, sync the data, and your agent can query it alongside your app data.

​
Query capabilities

Agents with MCP data access can perform powerful queries across your data:
CapabilityExample questionWhat happens
Filter”Show deals with status won”Filters records by field value
Sort”Show deals sorted by amount, highest first”Orders results by a field
Search”Find contacts at Acme Corp”Searches text fields
Date ranges”Deals closing this month”Filters by date ranges
Numeric ranges”Deals over $10,000”Filters by numeric thresholds
Limits”Show the top 5 deals”Limits result count
Combined filters”Open deals over $10k closing this quarter”Applies multiple filters at once
Aggregate”What’s the average deal size by status?”Groups and calculates sums, averages, counts
Join across collections”Show deals with their contact details”Combines data from related collections
Insert”Add a new deal for Acme Corp”Creates new records
Update”Mark that deal as won”Modifies existing records

​
Scopes

By default, agents can access all collections in your app. Use scopes to restrict an agent to specific collections when you want to limit what data it can see.

​
When to use scopes

  • Customer-facing agents — restrict to only the data relevant to the user’s context
  • Role-specific agents — a sales agent only needs deals and contacts, not HR data
  • Privacy-sensitive apps — limit access to prevent agents from exposing sensitive data

​
Prompt examples

Give the Sales Coach access to only deals and contacts.
It shouldn't see employee or payroll data.

Restrict the support agent's data access to orders
and tickets only.
If you don’t specify scopes, your agent can access all app collections. This is fine for most internal tools — only add scopes when you need to restrict access.

​
Prompt examples

Give the Sales Coach agent access to deals and contacts
so it can look up pipeline data and find contact information.

Add data access to the support agent so it can look up
orders by order number and check order status.

Let the HR assistant query employee records and
time-off requests.
Your app must be built with data models before agents can access data. The MCP Server connects to your existing collections. Build your app first, then create the agent.

​
Managing data access

You can update what data an agent can access through follow-up prompts:

​
Expanding access

Give the Sales Coach access to the products data
so it can answer questions about pricing.

​
Restricting access

Restrict the Sales Coach to only deals and contacts.
Remove access to everything else.

​
Adding write capabilities

Let the support agent update order status
and add notes to customer records.

​
Best practices

Begin by giving agents the ability to read and query data. Add write capabilities (inserting or updating records) only when needed.
Internal agents usually don’t need scopes — they can access everything. For customer-facing agents, use scopes to restrict access to only the relevant collections.
A sales agent needs deals and contacts. A support agent needs orders and tickets. Keep access relevant to what the agent does.
Data access handles live data queries. Knowledge bases handle static reference material. Together, an agent can look up a customer’s order and reference your return policy to answer a question.

​
Learn more

Creating agents

Set up agent name, instructions, and behavior

Knowledge bases

Add document references to your agent

Copilot

Embed the agent in your app

Data models

How app data is structured

Datasets

Group external data sources and attach them to your app