Integrations/npm

Control what your AI agents do in npm.

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

Request early accessSee how it works →
npm
Release Agent
Distribution tags Account areaOffReadFull use
Package metadata Account areaOffReadFull use
Publishing Account areaOffReadFull use
Publish and unpublish packages
What agents can do

Set what each agent can do across your account.

Each area of npm, like distribution tags, package metadata, or publishing, 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 package metadata and download counts in that area. It can't change anything.
Full use
Manage and update
The agent can manage distribution tags in that area.

Some actions stay off until explicitly turned on

Each one ships or removes published code that others depend on, or hands out access, so it could override the limits set elsewhere.

Publishing new versionsUnpublishing or deprecating versionsChanging access tokens
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 npm 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 and manage distribution tags in a single area
Example

A package release agent.

A release agent manages distribution tags and can read package metadata, but it can't publish a new version or change access tokens.

Distribution tags Account areaOffReadFull use
Package metadata Account areaOffReadFull use
Publishing Account areaOffReadFull use

Manage access

ALLOWEDRelease Agent updated a record in Distribution tags
ALLOWEDRelease Agent read the Package metadata
BLOCKEDRelease Agent tried to open Publishing, 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 npm, so they never hold your npm keys and never reach npm directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and publishing packages 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 npm 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 package or tag, and the decision. The record is readable and can't be edited after the fact.

Questions

npm, answered.

Does connecting npm hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your npm, and you decide which areas, like distribution tags or metadata, 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 publish or unpublish our packages?+
Not unless you turn it on. Publishing new versions, unpublishing or deprecating versions, and changing access tokens are held off by default, so an agent can read and manage tags where you allow without ever shipping or removing published 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 npm 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 npm, and the blocked attempt lands in the activity record with the reason.
How do we connect npm?+
An admin connects the company's npm 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 npm, 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 →