Field report 5 · AI governance

Microsoft 365 and AI: the value lies in control, not in access

How AI assistants get access to mail, calendar and documents without an all-or-nothing permission.

Status
Built Built and proven in our own use.
Published
Publisher
SIMO GmbH, Aschaffenburg, Germany

Starting questionHow do we give AI assistants access to mail, calendar and documents without granting all or nothing?

What we built

We built an access layer for Microsoft 365 based on the Model Context Protocol. It has several layers: tools with a fixed scope, tenant isolation, rate limiting, a need-to-know filter that detects personal and sensitive content, and logging of every access.

Development spans more than 200 revisions since April 2026.

What it means for business architecture

Sooner or later the platform vendor will offer mailbox access itself. What remains is the question of who may pass which content to which model, and how to prove it. That question belongs in the architecture of AI use.

Learnings

  1. With access layers, what counts is how they control, not how much they can do.
  2. Sensitive content has to be detected before it reaches a model. Afterwards it is too late.
  3. Open protocols let you switch models later instead of tying yourself to one vendor.
  • Microsoft 365
  • Model Context Protocol
  • need-to-know
  • logging

Matching consulting service

From the Lab into consulting.

What we trial in the Lab, SIMO GmbH puts into practice as consultants: Business Data Strategy & Architecture for AI, following the Zero Friction Data Flow principle. These services relate to this report:

45 minutes, free of charge, with the SIMO GmbH consultants. The form is on simo-online.com.

More reports on the same topic