Read teams and channels, and send channel and chat messages, in Microsoft Teams via the Microsoft Graph API.
Microsoft Teams ships in the w6w first-party pack. It declares 16 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.teamsMicrosoft Teams is where a lot of internal business communication happens, and this app reads teams and channels and sends channel and chat messages through the Microsoft Graph API.
It covers finding your way around a tenant’s Teams structure — listing teams you belong to, their channels, and the members of both — then posting into a channel or replying to an existing message thread. On the chat side, listing existing one-to-one and group chats, reading their messages, and sending a new message are all covered by a single permission, with none of the admin-consent friction channel reading requires.
Microsoft’s own permission model creates a real asymmetry worth knowing before you build around it: a workflow can post to a channel with no administrator involved at all, but reading channel messages back needs a tenant administrator’s consent first. This app is honest about that split rather than requesting one broad scope and hoping it works. It is scoped to messaging and membership — creating teams or channels, editing or deleting sent messages, and meetings or calls are all separate surfaces this app does not touch.
Three routes to the same 16 actions. The Workflow tab is generated from Microsoft Teams's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
list-channel-messages List the root messages in a channel, optionally with their replies inlined.
list-message-replies List the replies to one channel message. The root message is not included.
reply-to-channel-message Post a reply to an existing message in a team channel.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Microsoft Teams's real ids.
{
"manifestVersion": "2",
"name": "teams-example",
"steps": [
{
"id": "add-team-member",
"uses": {
"app": "io.w6w.teams",
"action": "add-team-member",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"teamId": "<teamId>",
"user": "<user>"
}
}
]
}add-team-member get-channel get-channel-message get-primary-channel get-team +11 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Microsoft Teams, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Microsoft Teams. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "send-channel-message",
payload: {
teamId: "<value>",
channelId: "<value>",
content: "<value>",
// contentType: "<value>",
// importance: "<value>",
// subject: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action send-channel-message --payload '{"teamId":"<value>","channelId":"<value>","content":"<value>"}' Give an AI agent Microsoft Teams — without giving it Microsoft Teams's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.teams#add-team-member",
"input": {
"teamId": "<teamId>",
"user": "<user>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Microsoft Teams connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Microsoft Teams's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Microsoft Teams itself is MIT, and the runtime that executes it is source-available (FSL).
Microsoft Teams declares its own checks, so its health is a property of the app rather than something the host guesses at.