Integrations/MongoDB Atlas
M

Control what your AI agents do in MongoDB Atlas.

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

Request early accessSee how it works →
MMongoDB Atlas
Infra Agent
Database users Data areaOffReadFull use
Clusters Data areaOffReadFull use
Network access Data areaOffReadFull use
Change network access
What agents can do

Set what each agent can do across your Atlas project.

Each area of MongoDB Atlas, like clusters, database users, or network access, 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 read cluster and project details in that area. It can't change anything.
Full use
Create and update
The agent can create and update records in that area, like database users.

Some actions stay off until explicitly turned on

Each one removes data for good or opens up who can reach your database, so it could override the limits set elsewhere.

Deleting clusters or projectsChanging network access rulesRemoving database users
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 MongoDB Atlas 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, create, and update records in a single area
Example

A database infrastructure agent.

An infra agent manages database users and can read your clusters, but it can't change network access or delete clusters.

Database users Data areaOffReadFull use
Clusters Data areaOffReadFull use
Network access Data areaOffReadFull use

Manage access

ALLOWEDInfra Agent created a record in Database users
ALLOWEDInfra Agent read a record in Clusters
BLOCKEDInfra Agent tried to open Network access, 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 MongoDB Atlas, so they never hold your MongoDB Atlas keys and never reach MongoDB Atlas directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and changing network access 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 MongoDB Atlas 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 cluster or user, and the decision. The record is readable and can't be edited after the fact.

Questions

MongoDB Atlas, answered.

Does connecting MongoDB Atlas hand Bollard AI your whole project?+
Only the areas you allow. An admin connects your MongoDB Atlas, and you decide which areas, like clusters or database users, 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 open up who can reach our database?+
Not unless you turn it on. Changing network access rules and deleting clusters are held off by default, so an agent can manage users where you allow without ever opening up access or removing data, 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 MongoDB Atlas 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 MongoDB Atlas, and the blocked attempt lands in the activity record with the reason.
How do we connect MongoDB Atlas?+
An admin connects the company's MongoDB Atlas 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 MongoDB Atlas, 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 →