AI Agents Are First-Class Users in OnAirFlow

AI agents are first-class users in OnAirFlow. An agent gets its own account in your organization, its own name in the show event log, and its own revocable credentials. Agents can perform the documented rundown actions over REST or hosted MCP. Agent users do not count toward the human seat limit.

What "first-class" actually means

Documented agent writes create activity-log entries attributed to the agent user.

Story work. Agents can create, update, and move stories through the rundown actions documented for REST and hosted MCP.

Column management. Agents with the required access can create, rename, and delete columns, and move stories between columns.

Attachment uploads. With Google Drive connected, REST agent uploads support files up to 50MB; hosted MCP uploads support up to 15MB decoded.

Two ways to connect

Hosted MCP for Claude, ChatGPT, or Grok

Add our MCP server as a custom connector:

https://api.onairflow.com/mcp

Connect Claude, ChatGPT, or Grok through OnAirFlow's hosted MCP endpoint, or use another compatible MCP client. Provider setup and limits apply. OAuth connections do not require an OnAirFlow API key.

Each connection shows up as its own named agent under Settings → AI → Assistants, and you (or an admin) can revoke it there any time. Then you just talk to your rundown: "what's on tomorrow's show?", "file these three stories into Ideas", "move the weather block up."

Scoped keys, if you run your own agents

If you run an agent fleet — Claude Code, Cursor, a cron job, anything that speaks HTTPS — mint a key instead. Go to Settings → AI → Agents & keys, create an agent, and mint a key with the scopes you choose: read-only, or read + write. Keys are shown exactly once and stored hashed, like a password.

From there, it's plain REST with a bearer token, or the same hosted MCP server with the key in a header. The settings page generates ready-to-paste config for both when you mint. There's also a downloadable agent skill that teaches Claude the endpoint shapes, field rules, and safety rails before its first call.

Eleven MCP tools cover the whole surface: shows, stories, columns, and attachments — including base64 file upload straight onto a story.

The part your engineers will ask about

Access is default-deny. Agent credentials reach the rundown surface — shows, stories, columns, attachments — and nothing else. Billing, user management, org settings, and exports are off-limits by construction. Out-of-scope requests get a flat 403.

Documented writes are on the record. Documented agent writes create activity-log entries attributed to the agent user.

Revocation is instant. Keys can be revoked or deactivated from the settings page the moment something feels off; OAuth connections die from the Connections list. No deploy, no support ticket.

Concurrent edits don't clobber. The API uses the same per-field conflict detection our human editors get. If an agent and a producer touch the same field, the second writer gets a conflict response and re-reads — nobody silently overwrites the control room.

Uploads land in your storage. Agent file uploads go to your organization's connected Google Drive — your storage, your retention rules, never our metered buckets.

Why it works this way

OnAirFlow owns the rundown and the access boundary. External agents receive their own accounts, scopes, activity attribution, and revocable credentials. The agent chooses what to do within the documented surface and the permissions it has been given.

Available today

Agent users do not count toward the human seat limit. OnAirFlow adds no AI usage charge; your assistant provider's plan and limits apply.

• Meet the agents — what they do and the full trust model
• Connect your first agent — hosted MCP and scoped-key setup
• REST API reference — every endpoint, every error, no surprises

Start your 7-day trial — no credit card.