OneDrive MCP | Oauth 2.0 OneDrive connector for AI agents

CALL ANY TOOL

List, search, download, share files, and create folders in OneDrive.

onedrive_files_list

List files

List files in a OneDrive folder or the root.

Parameters

Name

Type

Required

Description

folder_id

string

Optional

Folder ID (defaults to root)

limit

integer

Optional

Max files

onedrive_file_get

Get file

onedrive_file_download

Download file

onedrive_files_search

Search files

onedrive_file_share

Share file

onedrive_folder_create

Create folder

Build your Agent

Drop the toolkit in, point it at the user, and your document agent can use OneDrive from the first run.

Copied

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: ["onedrive"], toolNames: ["onedrive_files_list", "onedrive_file_get", "onedrive_file_download"] },
  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 });

Copied

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: ["onedrive"], toolNames: ["onedrive_files_list", "onedrive_file_get", "onedrive_file_download"] },
  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: ["onedrive"], toolNames: ["onedrive_files_list", "onedrive_file_get", "onedrive_file_download"] },
  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 }],
});

Copied

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/onedrive",
    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 OneDrive.

Search & recall

Copy the prompt

Copied

Find all PDFs shared with me this week.

Copy the prompt

Copied

List files in [folder name].

Copy the prompt

Copied

Get metadata for [file name].

Copy the prompt

Copied

Search OneDrive for [keyword].

Action & sharing

Copy the prompt

Copied

Download [file name] as PDF.

Copy the prompt

Copied

Create a shared link for [file].

Copy the prompt

Copied

Create a folder named [name] in [parent].

Copy the prompt

Copied

Share [file] with [email] as editor.

Audits & reporting

Copy the prompt

Copied

Which files were modified today?

Copy the prompt

Copied

List files owned by [email].

Copy the prompt

Copied

Find files larger than 50MB.

Copy the prompt

Copied

Show files shared with anyone outside the org.

SEE HOW AUTH WORKS

Users authorize OneDrive once. Their credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

OneDrive

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

OneDrive

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

OneDrive

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

OneDrive

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 document agents and MCP connectors. Working code, live demos, fork what fits.

SUPPORT

Support triage agent

Read Zendesk tickets, fetch runbooks from Notion, and route to the right Slack channel with a drafted response.

SUPPORT

Support ticket automation (Google ADK)

Google ADK agent that classifies Zendesk tickets, pulls Notion context, and posts to Slack. End-to-end ticket handoff.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

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.

OneDrive 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 OneDrive 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 OneDrive 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 OneDrive?

Yes. Pass a tool name filter to listScopedTools so the document agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches OneDrive.

What happens when a user revokes OneDrive 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 access files in SharePoint document libraries through OneDrive?

Yes, if the authorizing user has access to the SharePoint site. Files synced via OneDrive for Business follow the same Microsoft Graph permissions. SharePoint sites the user hasn't been granted access to remain inaccessible.

OneDrive

Tools your document agent reaches for on OneDrive, scoped per user.