Integrations/Mercury
M

Control what your AI agents do in Mercury.

Let your team build AI agents for Mercury. Bollard AI controls what each one can do, and moving money stays off by default.

MMercury
Finance Agent
Recipients Area of the accountOffReadFull use
Transactions Area of the accountOffReadFull use
Send money ActionOffReadFull use
Send money
What agents can do

Set what each agent can do in every area of your account.

Each area of Mercury, like recipients or transactions, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied, and sending money is a separate switch.

Off
No access
The agent can't open that area or see what's in it.
Read
Read-only
The agent can read records in that area, like transactions or recipients. It can't change anything.
Full use
Create and update
The agent can create and update records in that area, like adding a recipient.

Some actions stay off until explicitly turned on

Each one moves money out of your account, so it could override the limits set on individual areas.

Sending money and transfersCancelling cardsChanging recipient bank details
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 Mercury a single time. Bollard AI lays out the areas of the 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, create, and update records in a single area
Example

A finance operations agent.

A finance agent manages recipients and can read your transactions, but it can't send money.

Recipients Area of the accountOffReadFull use
Transactions Area of the accountOffReadFull use
Send money ActionOffReadFull use

Manage access

ALLOWEDFinance Agent added a record in Recipients
ALLOWEDFinance Agent read a transaction
BLOCKEDFinance Agent tried to send money, 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 Mercury, so they never hold your Mercury keys and never reach Mercury directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and sending money 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 Mercury 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 recipient or transaction, and the decision. The record is readable and can't be edited after the fact.

Questions

Mercury, answered.

Does connecting Mercury hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Mercury, and you decide which areas, like recipients or transactions, 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 send money on its own?+
Not unless you turn it on. Sending money and transfers is held off by default, so an agent can manage recipients and read transactions without ever moving money out of your account, 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 Mercury 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 Mercury, and the blocked attempt lands in the activity record with the reason.
How do we connect Mercury?+
An admin connects the company's Mercury once. Bollard AI seals the connection and lays out the areas of the 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 Mercury, without the risk.

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