Microsoft Teams

Live

OAUTH 2.0

COLLABORATION

Communication

Every team channel, meeting, and conversation your organization runs lives in Microsoft Teams. Teams MCP gives your agent authenticated access to collaboration data scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Microsoft Teams account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: Permissions enforced. 90-day audit trail.
Microsoft Teams
agent · Acme Q3
Run
Summarize what was discussed in the #engineering channel this week.
S
teams_messages_list
84ms
Collaboration agent
Engineering channel this week: 3 topics. Deploy freeze for Nov 1 release (42 messages, decision: approved). Auth service incident post-mortem (18 messages, 3 action items assigned). Q4 roadmap review scheduled for Friday.
Sources: #engineering, this week
teamsmcp
63 messages
18:29
Message Claude...

Tools your collaboration agent reaches for on Microsoft Teams, scoped per user.

CALL ANY TOOL
List teams and channels, read and send messages, and retrieve upcoming meeting schedules.
microsoftteams_add_channel_member
Add channel member
Add a user as a conversationMember of a Microsoft Teams channel. This operation is only allowed for channels with a membershipType of private or shared; standard channel membership is derived from team membership instead.
Parameters
Name
Type
Required
Description
channel_id
string
Required
The unique identifier of the Teams channel.
team_id
string
Required
The unique identifier of the Microsoft Teams team.
user_id
string
Required
The Azure AD object ID of the user to add. This is the user's unique identifier in Microsoft Entra ID, not their email address.
role
string
Optional
The role to assign to the added user. Valid values: 'member' or 'owner'. Defaults to 'member'.
microsoftteams_approve_time_off_request
Approve time off request
microsoftteams_archive_channel
Archive channel
microsoftteams_clone_team
Clone team
microsoftteams_create_channel
Create channel
microsoftteams_create_online_meeting
Create online meeting
microsoftteams_create_shift_swap_request
Create shift swap request
microsoftteams_delete_channel
Delete channel
microsoftteams_delete_channel_tab
Delete channel tab
microsoftteams_delete_online_meeting
Delete online meeting
microsoftteams_get_channel
Get channel
microsoftteams_get_chat
Get chat
microsoftteams_get_meeting_transcript_content
Get meeting transcript content
microsoftteams_list_all_teams
List all teams
microsoftteams_list_channel_messages
List channel messages
microsoftteams_list_chat_members
List chat members
microsoftteams_list_installed_apps
List installed apps
microsoftteams_list_meeting_transcripts
List meeting transcripts
microsoftteams_list_shifts
List shifts
microsoftteams_pin_channel_message
Pin channel message
microsoftteams_remove_channel_email
Remove channel email
microsoftteams_reply_to_channel_message
Reply to channel message
microsoftteams_restore_channel_message
Restore channel message
microsoftteams_search_messages
Search messages
microsoftteams_send_channel_message
Send channel message
microsoftteams_set_preferred_presence
Set preferred presence
microsoftteams_uninstall_app
Uninstall app
microsoftteams_update_channel
Update channel
microsoftteams_update_chat
Update chat
microsoftteams_update_shift
Update shift

For more tools, view docs.

Build your Agent
Drop the toolkit in, point it at the user, and your collaboration agent can use Microsoft Teams from the first run.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["teams"], toolNames: ["teams_teams_list", "teams_channels_list", "teams_messages_list"] },
pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
name: t.tool.definition.name,
description: t.tool.definition.description,
schema: z.object({}).passthrough(),
func: async (args) => {
const { data } = await sk.tools.executeTool({
toolName: t.tool.definition.name,
identifier: "user_123",
params: args,
});
return JSON.stringify(data);
},
}));

const agent = createReactAgent({ llm, tools: lcTools });
import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["teams"], toolNames: ["teams_teams_list", "teams_channels_list", "teams_messages_list"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
type: "function",
function: {
name: t.tool.definition.name,
description: t.tool.definition.description,
parameters: t.tool.definition.input_schema,
},
}));

const resp = await openai.responses.create({
model: "gpt-4o", input: prompt, tools: llmTools,
});
import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["teams"], toolNames: ["teams_teams_list", "teams_channels_list", "teams_messages_list"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
name: t.tool.definition.name,
description: t.tool.definition.description,
input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
model: "claude-sonnet-4-6", max_tokens: 1024,
tools: llmTools,
messages: [{ role: "user", content: prompt }],
});
import { Agent } from "@google/adk/agents";
import {
MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
connectionParams: new StreamableHTTPConnectionParams({
url: "https://mcp.scalekit.com/teams",
headers: { Authorization: `Bearer ${userScopedToken}` },
}),
});

const agent = new Agent({
name: "agent", model: "gemini-2.0-flash",
tools: await toolset.getTools(),
});
Try these prompts
Paste any prompt into your agent to start using Microsoft Teams.
Messages & channels
Copy the prompt
Copied
Summarize #general channel messages this week.
Copy the prompt
Copied
List all channels in [team name].
Copy the prompt
Copied
Post to [channel]: [message].
Copy the prompt
Copied
Find messages mentioning [topic] this week.
Teams & meetings
Copy the prompt
Copied
List all teams I'm a member of.
Copy the prompt
Copied
What meetings do I have this week?
Copy the prompt
Copied
Which channels were most active today?
Copy the prompt
Copied
List all messages from [person] this week.
Reporting
Copy the prompt
Copied
Most active channels this month.
Copy the prompt
Copied
Summary of [channel] discussions this sprint.
Copy the prompt
Copied
Which topics came up most in [team] this week?
Copy the prompt
Copied
List all messages with action items assigned.
SEE HOW AUTH WORKS
Users authorize Microsoft Teams once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Microsoft Teams
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Microsoft Teams
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Microsoft Teams
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Microsoft Teams
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
Same per-user auth pattern across other collaboration agents and MCP connectors. Working code, live demos, fork what fits.
Engineering Teams
Slack triage
Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.
Support and Ops Teams
Support triage agent
Fetches new Zendesk tickets, classifies them by type and urgency, searches the Notion knowledge base for an answer, and routes what it cannot resolve to Slack. Every call runs on the support agent's own delegated OAuth.
Support and Ops Teams
Meeting prep
Pulls agenda, participant context, and open action items before every meeting.
GTM and RevOps Teams
Competitive intelligence briefing agent
Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.
Test other agents
Same per-user auth pattern across other collaboration agents and MCP connectors. Working code, live demos, fork what fits.
ENGINEERING
Slack triage agent
Classify new Slack messages as bugs or support requests, file the GitHub issue or Zendesk ticket, and reply in the thread.
SUPPORT
Support triage agent
Classify new Zendesk tickets, search the Notion knowledge base for an answer, and route what it cannot resolve to Slack.
OPS
Meeting prep agent
Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.
GTM
Competitive intelligence briefing agent
Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.
// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Microsoft Teams today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Microsoft Teams as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.
Where is the Microsoft Teams oauth 2.0 stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.
Can I limit what the agent is allowed to do in Microsoft Teams?
Yes. Pass a tool name filter to listScopedTools so the collaboration agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Microsoft Teams.
What happens when a user revokes Microsoft Teams access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent read private channels the user is not a member of?
No. The agent only accesses teams and channels the authorizing user belongs to. Private channels the user has not been added to are not returned. Microsoft 365 channel membership rules apply at every call.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""teams"": {
""url"": ""https://mcp.scalekit.com/teams"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.teams]
url = ""https://mcp.scalekit.com/teams""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""teams"": {
""url"": ""https://mcp.scalekit.com/teams"",
""type"": ""http""
}
}
}