Microsoft 365 connector for AI agents

Tools your productivity agent reaches for on Microsoft 365, scoped per user.

CALL ANY TOOL

317 tools across Microsoft 365: read, send, and organize Outlook mail, manage calendars, contacts, and To Do tasks, message in Teams, work with OneDrive and SharePoint files, and edit Excel workbooks.

microsoft365_excel_add_table_column

Excel add table column

Add a new column to an existing Excel table in OneDrive. Optionally specify the column name, its zero-based insertion index (null = append at end), and initial cell values as a 2D array (first row is the header). Returns the created column object.

Parameters

Name

Type

Required

Description

item_id

string

Required

OneDrive item ID of the Excel (.xlsx) file. Example: '01BYE5RZ6QN3ZWBTUFOFD3GSPGOHDJD36K'.

table_id

string

Required

Name or ID of the table to add the column to. Example: 'Table1' or the GUID assigned by Excel.

index

integer

Optional

Zero-based index position at which to insert the column. Null or omitted means append the column at the right end of the table. Example: 0 inserts as the first column.

name

string

Optional

Display name for the new column header. If omitted, Excel auto-generates a name (e.g., 'Column1'). Example: 'Revenue'.

session_id

string

Optional

Optional workbook session ID from createSession. When provided, sent as the workbook-session-id header. Example: 'cluster=SN2&session=...'.

values

array

Optional

2D array of initial cell values for the column, including the header row in the first element. Example: [["Header"],["row1val"],["row2val"]]. Each inner array is one row. If omitted, the column is created empty.

microsoft365_excel_calculate_workbook

Excel calculate workbook

microsoft365_excel_create_chart

Excel create chart

microsoft365_excel_delete_chart

Excel delete chart

microsoft365_excel_get_range

Excel get range

microsoft365_excel_list_charts

Excel list charts

microsoft365_excel_update_chart

Excel update chart

microsoft365_onedrive_discard_checkout

Onedrive discard checkout

microsoft365_onedrive_search_drive_items

Onedrive search drive items

microsoft365_onedrive_upload_large_file

Onedrive upload large file

microsoft365_onenote_get_page_content

Onenote get page content

microsoft365_outlook_create_calendar

Outlook create calendar

microsoft365_outlook_create_mail_folder

Outlook create mail folder

microsoft365_outlook_delete_calendar_group

Outlook delete calendar group

microsoft365_outlook_forward_event

Outlook forward event

microsoft365_outlook_get_mail_tips

Outlook get mail tips

microsoft365_outlook_list_contacts

Outlook list contacts

microsoft365_outlook_send_draft_message

Outlook send draft message

microsoft365_outlook_todo_checklist_items_delete

Delete outlook todo checklist items

microsoft365_outlook_todo_tasks_update

Update outlook todo tasks

microsoft365_outlook_update_message

Outlook update message

microsoft365_powerpoint_read_presentation

Powerpoint read presentation

microsoft365_sharepoint_create_site_page

Sharepoint create site page

microsoft365_sharepoint_get_site

Sharepoint get site

microsoft365_sharepoint_list_followed_sites

Sharepoint list followed sites

microsoft365_sharepoint_publish_site_page

Sharepoint publish site page

microsoft365_sharepoint_remove_group_member

Sharepoint remove group member

microsoft365_sharepoint_renew_webhook

Sharepoint renew webhook

microsoft365_teams_archive_channel

Teams archive channel

microsoft365_teams_set_preferred_presence

Teams set preferred presence

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Microsoft 365 tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["microsoft365"], toolNames: [
    "microsoft365_outlook_search_messages",
    "microsoft365_outlook_find_meeting_times",
    "microsoft365_onedrive_search_drive_items"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find a 30-minute slot tomorrow when Priya and I are both free" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["microsoft365"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find a 30-minute slot tomorrow when Priya and I are both free" }],
  tools,
});

// Execute the tool call with the user's vaulted Microsoft 365 token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["microsoft365"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find a 30-minute slot tomorrow when Priya and I are both free" }],
  tools,
});

// Tool call runs with the user's vaulted Microsoft 365 token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["microsoft365"] }, pageSize: 100,
});

const agent = new Agent({
  name: "scheduling_agent",
  model: "gemini-2.5-pro",
  instruction: "Microsoft 365 tools scoped to this user",
  tools,
});

await agent.run("Find a 30-minute slot tomorrow when Priya and I are both free");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Microsoft 365 tool. Click to copy, paste into your agent, done.

Mail

Copy the prompt

Copied

Search my inbox for emails about the Q3 budget.

Copy the prompt

Copied

Draft a reply to the latest message from Priya.

Copy the prompt

Copied

Move this week's newsletters into my Reading folder.

Calendar and meetings

Copy the prompt

Copied

Find a 30-minute slot tomorrow when Priya and I are both free.

Copy the prompt

Copied

Show my calendar for the rest of this week.

Copy the prompt

Copied

List the transcripts from yesterday's Teams project sync.

Files and Teams

Copy the prompt

Copied

Find the latest Q3 review deck in my OneDrive.

Copy the prompt

Copied

Read cells A1:F20 from the Budget sheet in this workbook.

Copy the prompt

Copied

Post a launch update to the General channel of the Marketing team.

SEE HOW AUTH WORKS

Each user signs in to Microsoft 365 once; Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Microsoft 365

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

Store

Their

Microsoft 365

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

Resolve

When your agent calls a

Microsoft 365

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

Audit

Every

Microsoft 365

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

See the same per-user auth pattern across other productivity and collaboration connectors.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

People Ops and HR teams

Performance review collector

Collects review feedback from Airtable and Google Forms scoped to each manager's direct reports, writes per-employee summaries to Notion, and DMs the manager a Slack digest.

People Ops and HR teams

Offer letter routing agent

Drafts the offer in PandaDoc, blocks on the hiring manager's approval in Slack, then emails the candidate their e-signature link. Every call runs as the recruiter who triggered it, never a shared HR bot.

GTM and RevOps Teams

Deal room sync

Pulls opportunity context from Salesforce, captures key decisions from Slack, and syncs a running summary to the deal room doc in Google Drive, but only when the deal actually changed.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Microsoft 365 token looks fine in a demo. In production every sent email and calendar change looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Microsoft 365 today. Ten connectors 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 365 as the user or through a shared service account?

As the user. Each user signs in to Microsoft 365 once, and Scalekit stores and refreshes their tokens. Audit logs attribute every action to that user, not a shared service account.

Where is the Microsoft 365 OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Microsoft 365?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example only the Outlook calendar tools for a scheduling agent. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Microsoft 365 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.

Which Microsoft 365 apps does the connector cover?

Outlook mail, calendar, contacts, and To Do, Teams chats, channels, meetings, and shifts, OneDrive, SharePoint sites and lists, and Excel, Word, PowerPoint, and OneNote. That is 317 tools: 127 read, 150 write, and 40 destructive. Expose only the apps your agent needs in toolNames.