MCP server for Microsoft 365 Outlook (mail + calendar) with audit-preserving drafts and never-auto-send.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-server-outlook","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
<!-- SPDX-License-Identifier: MIT OR Apache-2.0 --> # mcp-server-outlook [](https://pypi.org/project/mcp-server-outlook/) [](https://pypi.org/project/mcp-server-outlook/) [](https://pypi.org/project/mcp-server-outlook/) [](https://github.com/XMV-Solutions-GmbH/outlook-mcp/blob/main/LICENSE) [](https://github.com/XMV-Solutions-GmbH/outlook-mcp/actions/workflows/ci.yml) [](https://codecov.io/gh/XMV-Solutions-GmbH/outlook-mcp) [](https://github.com/XMV-Solutions-GmbH/outlook-mcp/issues) > **In one sentence:** an [MCP](https://modelcontextprotocol.io) server that lets AI coding agents like Claude Code read your Microsoft 365 inbox and calendar — and **draft** emails and meetings on your behalf — **without ever auto-sending and without breaking audit attribution**. ## What is this for? You're a consultant, contractor, or operator working across multiple Microsoft 365 tenants. You'd love to let AI agents triage your inbox, summarise calendar conflicts, and draft replies — but every existing option is bad: - **Account-bound claude.ai connectors** force one tenant per connector — useless if you're in three tenants at once with the same Claude account. - **IMAP/SMTP scrapers** lose calendar context, lose attribution (mail appears as "anonymous client"), bypass modern auth. - **Auto-sending agents** are scary in regulated environments — one wrong tool call and y…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.