Integrations/Supabase

Control what your AI agents do in Supabase.

Let your team build AI agents for Supabase. Bollard AI controls what each one can do, area by area.

Request early accessSee how it works →
Supabase
Ops Agent
Database Project areaOffReadFull use
Edge Functions Project areaOffReadFull use
Secrets Project areaOffReadFull use
Manage secrets and functions
What agents can do

Set what each agent can do across your project.

Each area of Supabase, like the database, functions, or secrets, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.

Off
No access
The agent can't see that part of your project.
Read
Read-only
The agent can run read-only queries and read details in that area. It can't change anything.
Full use
Query and update
The agent can run queries and update records in that area.

Some actions stay off until explicitly turned on

Each one exposes secrets, removes a project for good, or changes what runs, so it could override the limits set elsewhere.

Managing secretsDeploying or deleting Edge FunctionsDeleting a project
Set up & manage

Connect once. Manage everyone from there.

Connect once, then control access person by person. No new keys to hand out.

Step 1 · Set up

Connect once, company-wide

An admin connects your company's Supabase a single time. Bollard AI lays out the areas of your project, and anything you don't allow stays out of reach for every agent.

Step 2 · Manage

Control access per person and agent

From one dashboard, set what every person and their agents can reach. Change it any time, with no new keys for anyone.

OffNo access
ReadRead-only
Full useRead, query, and update records in a single area
Example

A database operations agent.

An ops agent runs queries on the database and can read your Edge Functions, but it can't open secrets or deploy functions.

Database Project areaOffReadFull use
Edge Functions Project areaOffReadFull use
Secrets Project areaOffReadFull use

Manage access

ALLOWEDOps Agent ran a query on the Database
ALLOWEDOps Agent read the Edge Functions
BLOCKEDOps Agent tried to open Secrets, denied by default

Monitor activity

The security model

Top-tier security.

Bollard AI is access control for AI agents. It sits between your agents and Supabase, so they never hold your Supabase keys and never reach Supabase directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to Supabase. Bollard AI checks each one against your rules and passes only the allowed requests through.

Denied by default

Every area starts off-limits, and managing secrets is held back on top of that. An agent gets in only where you've allowed it, and anything Bollard AI doesn't recognise is refused and held for review, never waved through on a guess.

Your keys stay sealed

Your Supabase keys are sealed in a vault unique to your company and never shown again. Bollard AI unlocks them only for the instant an allowed request needs it.

Activity you can read

Every attempt is recorded in plain English: who or which agent, what they tried, which table or function, and the decision. The record is readable and can't be edited after the fact.

Questions

Supabase, answered.

Does connecting Supabase hand Bollard AI your whole project?+
Only the areas you allow. An admin connects your Supabase, and you decide which areas, like the database or functions, each agent can reach. Bollard AI doesn't browse or copy your project. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent read our secrets or deploy code?+
Not unless you turn it on. Managing secrets and deploying Edge Functions are held off by default, so an agent can query and update where you allow without ever touching secrets or shipping code, until you explicitly allow it.
Can an agent see more than the person who owns it?+
No. An agent reaches only what its owner reaches. An explicit Off always overrides an inherited permission.
Where do our Supabase keys live?+
Sealed in an encrypted vault, behind a key unique to your company. It's never shown again once connected, and Bollard AI unseals it only for the instant an allowed request needs it.
What happens when an agent tries something it's not allowed to do?+
Bollard AI blocks the request before it reaches Supabase, and the blocked attempt lands in the activity record with the reason.
How do we connect Supabase?+
An admin connects the company's Supabase once. Bollard AI seals the connection and lays out the areas of your project to set rules for. From then on, all management happens in the Bollard AI dashboard.
Early access

Put your team's agents to work in Supabase, without the risk.

We're onboarding our first development partners now. Tell us about your setup and we'll be in touch.

Request early accessAll integrations →