Ironbrain

Approve what matters. Automate the rest.

Critical MCP actions land in the Outbox. You decide which tools need human approval—and which may run without interrupting the flow.

Outbox

Confirm, edit, or reject before execution

3 pending
  • EM

    Reply with revised proposal timeline

    Toanna@acme.de
    SubjectFollowing up on the proposal

    Hi Anna — thanks for the call. Attached is the revised timeline…

    Approve Edit Reject
  • CA

    Agent moved the workshop · review before / after

    Approve Edit Reject
  • RD
    list_emails AllowAlways

    Ran automatically · your policy

How actions move through Ironbrain

Every connected agent hits one MCP endpoint. Your HITL policy decides: hold in the Outbox, or run on the auto path.

  • Clients — Cursor, Claude, and other MCP clients
  • Gate — Secrets stay server-side; the policy cascade applies
  • Split — RequireHitl goes to the Outbox; AllowAlways reaches your tools

Real controls, not a chat prompt

The Outbox mirrors what Ironbrain already ships: typed actions, editable payloads, before/after diffs, Approve / Edit / Reject, and a hard floor for external sends.

Approve action

Send email to anna@acme.de

pending
anna@acme.de
Following up on the proposal
Hi Anna — thanks for the call. Attached is the revised timeline for Q2…
Internal recipient Cursor MCP
Approve & send Save edits Reject

Approve action

Update appointment · Client workshop

UpdateAppointment

Agent moved the workshop. Review before / after, then approve.

Before
Title
Client workshop
When
Thu 14:00–16:00
Where
Room B
After
Title
Client workshop
When
Fri 10:00–12:00
Where
Room A
Approve Edit Refine in chat Reject

You set the approval policy

Every action has an HITL mode. It starts from a default and can be overridden for your organization and in your personal settings. Critical tools wait in the Outbox; the rest stay automatic.

RequireHitl

Always wait in the Outbox

PreferHitl

Ask when below threshold

AllowAuto

Run unless policy intervenes

AllowAlways

No approval (usually reads)

Toolbox, solutions, and consulting

Approval is the core product. Around it we offer building blocks, custom integrations, and advice for bringing AI into your stack.

Solutions

Individual solutions with deeper vertical integration for specific workflows—delivered by us or with partners, fitted to your processes.

Consulting

AI integration consulting and onboarding: we help you connect assistants to real systems safely—with Ironbrain or alongside other services.

One Outbox for every connected agent.

Interested in the platform, a custom solution, or consulting? Write to us.

hello@ironbrain.de