Connect Microsoft Teams to Claude Code

Make Claude post to channels and reply in threads in Microsoft Teams. From the terminal, inside the sessions where you already work.

Build my connector Talk to us

How do you connect Microsoft Teams to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Microsoft Teams, you add a Microsoft Teams MCP server: a small hosted service that exposes Microsoft Teams's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Microsoft Teams account. No API keys pasted into config files.

claude mcp add --transport http microsoft-teams https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Microsoft Teams once connected?

Full read-write Microsoft Teams access lets Claude post a message to a specific channel, reply inside an existing thread, send a direct or group chat, and react or mention people once you approve. The drafting and follow-up that used to mean switching apps and copy-pasting happen where the conversation already lives.

Post a message to a specific Teams channel after you approve it
Reply inside an existing channel thread, preserving the conversation
Send a direct or group chat message to teammates
Add a reaction or mention people to flag a message for attention
Search recent messages and propose a drafted summary to post back
Share a link or short update into the right channel on your behalf

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Microsoft Teams access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Microsoft Teams API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Microsoft Teams changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Microsoft Teams connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Microsoft Teams connector work in claude.ai and Claude Code?

Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Microsoft Teams account, so access always matches what that person can already see and do.

Do I need to host or maintain anything myself?

No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Microsoft Teams's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.

Is it safe to give a coding agent write access to Microsoft Teams?

Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Microsoft Teams account it signs in with. Revoking access is one click in Microsoft Teams.

More on the Microsoft Teams connector

Microsoft Teams connector for claude.ai Gmail + Claude Code Outlook + Claude Code Slack + Claude Code

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.

Build my connector Talk to us