Integrations/Uploadcare
U

Control what your AI agents do in Uploadcare.

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

Request early accessSee how it works →
UUploadcare
Media Agent
Files Account areaOffReadFull use
Groups Account areaOffReadFull use
Project Account areaOffReadFull use
Delete files in bulk
What agents can do

Set what each agent can do across your account.

Each area of Uploadcare, like files, groups, or project settings, 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 account.
Read
Read-only
The agent can read and list files and groups in that area. It can't change anything.
Full use
Upload and update
The agent can upload and tag files in that area.

Some actions stay off until explicitly turned on

Each one removes files for good or changes how your media is served, so it could override the limits set elsewhere.

Deleting files in bulkChanging project settingsPurging the delivery cache
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 Uploadcare a single time. Bollard AI lays out the areas of your account, 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, upload, and tag files in a single area
Example

A media library agent.

A media agent uploads and tags files and can read your groups, but it can't delete files in bulk or change project settings.

Files Account areaOffReadFull use
Groups Account areaOffReadFull use
Project Account areaOffReadFull use

Manage access

ALLOWEDMedia Agent uploaded a file in Files
ALLOWEDMedia Agent read a Group
BLOCKEDMedia Agent tried to open Project, 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 Uploadcare, so they never hold your Uploadcare keys and never reach Uploadcare directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and removing files in bulk 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 Uploadcare 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 file or group, and the decision. The record is readable and can't be edited after the fact.

Questions

Uploadcare, answered.

Does connecting Uploadcare hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Uploadcare, and you decide which areas, like files or groups, each agent can reach. Bollard AI doesn't browse or copy your account. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent delete our files in bulk?+
Not unless you turn it on. Deleting files in bulk, and changing project settings, are held off by default, so an agent can upload and tag files without ever removing media or changing how it is served, 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 Uploadcare 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 Uploadcare, and the blocked attempt lands in the activity record with the reason.
How do we connect Uploadcare?+
An admin connects the company's Uploadcare once. Bollard AI seals the connection and lays out the areas of your account 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 Uploadcare, 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 →