Integrations/Mastodon

Control what your AI agents do in Mastodon.

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

Request early accessSee how it works →
Mastodon
Social Agent
Drafts Account areaOffReadFull use
Timeline Account areaOffReadFull use
Followers Account areaOffReadFull use
Publish posts
What agents can do

Set what each agent can do across your account.

Each area of Mastodon, like drafts, timeline, or followers, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied, and posting is a separate switch.

Off
No access
The agent can't see that part of your account.
Read
Read-only
The agent can read your timeline and posts in that area. It can't change or post anything.
Full use
Draft and update
The agent can create and update drafts in that area.

Some actions stay off until explicitly turned on

Each one posts in public or changes who you follow and block, so it could override the limits set elsewhere.

Publishing postsDeleting postsFollowing or blocking accounts
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 Mastodon 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, draft, and update in a single area
Example

A social drafting agent.

A social agent writes drafts and can read your timeline, but it can't publish a post or follow accounts.

Drafts Account areaOffReadFull use
Timeline Account areaOffReadFull use
Followers Account areaOffReadFull use

Manage access

ALLOWEDSocial Agent updated a record in Drafts
ALLOWEDSocial Agent read the Timeline
BLOCKEDSocial Agent tried to publish a post, 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 Mastodon, so they never hold your Mastodon keys and never reach Mastodon directly.

Everything runs through Bollard AI

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

Denied by default

Every area starts off-limits, and posting 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 Mastodon 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 draft or post, and the decision. The record is readable and can't be edited after the fact.

Questions

Mastodon, answered.

Does connecting Mastodon hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your Mastodon, and you decide which areas, like drafts or timeline, 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 post in public on its own?+
Not unless you turn it on. Publishing posts, and following or blocking accounts, are held off by default, so an agent can write drafts and read your timeline without ever posting in public, 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 Mastodon 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 Mastodon, and the blocked attempt lands in the activity record with the reason.
How do we connect Mastodon?+
An admin connects the company's Mastodon 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 Mastodon, 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 →