Integrations/n8n

Control what your AI agents do in n8n.

Let your team build AI agents for n8n. Bollard AI controls what each one can do, workflow by workflow.

Request early accessSee how it works →
n8n
Ops Agent
lead-sync WorkflowOffReadFull use
reporting WorkflowOffReadFull use
billing WorkflowOffReadFull use
Delete workflows and credentials
What agents can do

Set what each agent can do in every workflow.

Each workflow gets one of three levels: Off, Read, or Full use. Anything not allowed is denied.

Off
No access
The agent can't see the workflow or that it exists.
Read
Read-only
The agent can read the steps and executions of that workflow. It can't change anything.
Full use
Build and update
The agent can build and update that workflow.

Some actions stay off until explicitly turned on

Each one removes automations for good, activates them, or exposes the credentials behind them, so it could override the limits set on individual workflows.

Deleting workflows or executionsPublishing or activating workflowsDeleting credentials
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 n8n a single time and chooses which workflows it covers. Any workflow left out 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, build, and update a single workflow
Example

An automation agent.

An ops agent edits the lead-sync workflow and can read reporting, but it can't open billing or delete a credential.

lead-sync WorkflowOffReadFull use
reporting WorkflowOffReadFull use
billing WorkflowOffReadFull use

Manage access

ALLOWEDOps Agent updated the lead-sync workflow
ALLOWEDOps Agent read the reporting workflow
BLOCKEDOps Agent tried to open billing, 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 n8n, so they never hold your n8n keys and never reach n8n directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to n8n. Bollard AI checks each one against your rules and passes only the allowed requests through.

Denied by default

Every workflow starts off-limits, and activating workflows 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 n8n 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 workflow or credential, and the decision. The record is readable and can't be edited after the fact.

Questions

n8n, answered.

Does connecting n8n hand Bollard AI all your workflows?+
Only what's connected. An admin chooses which workflows Bollard AI covers, and that sets the most any agent could reach. Bollard AI doesn't browse or copy your automations. It sits in front of them and checks every request the agents make, passing or blocking each one.
Can an agent activate workflows or read our credentials?+
Not unless you turn it on. Publishing or activating workflows, and deleting credentials, are held off by default, so an agent can build and read where you allow without ever switching automations on or touching credentials, 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 n8n 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 n8n, and the blocked attempt lands in the activity record with the reason.
How do we connect n8n?+
An admin connects the company's n8n once. Bollard AI seals the connection and builds the list of workflows 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 n8n, 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 →