Connect
Optimize
Secure
Microsoft OneDrive MCP Server
for AI Agents
Production-ready Microsoft OneDrive MCP server with 46 extensible actions — plus built-in authentication, security, and optimized execution.
Microsoft OneDrive MCP Server
Built by 
StackOne
StackOne 
Coverage
46 Agent Actions
Create, read, update, and delete across Microsoft OneDrive — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Microsoft OneDrive MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Microsoft OneDrive tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Microsoft OneDrive call.
Tools Discovery →What is the Microsoft OneDrive MCP Server?
A Microsoft OneDrive MCP server lets AI agents read and write Microsoft OneDrive data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Microsoft OneDrive MCP server ships with 46 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Microsoft OneDrive MCP Tools and Actions
Every action from Microsoft OneDrive's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Unified Files
- Upload Unified File
Upload a new file to Microsoft OneDrive using the StackOne unified upload schema
- List Unified Files
List unified files in Microsoft OneDrive with StackOne unified filters
- Get Unified File
Get a unified file by ID from Microsoft OneDrive with metadata mapped to the StackOne unified schema
- Download Unified File
Download the content of a unified file from Microsoft OneDrive
Unified Folders
- List Unified Folders
List unified folders from the root of the authenticated user's OneDrive
- Get Unified Folder
Get a unified folder by ID from Microsoft OneDrive
Unified Drives
- List Unified Drives
List unified drives available to the authenticated user in Microsoft OneDrive
- Get Unified Drive
Get a unified drive by ID from Microsoft OneDrive
Drive Items
- Copy Drive Item
Create a copy of a driveItem including any children
- Search Drive Items
Search for items in a drive
- Search Drive Items
Search for items in a drive
- Get Drive Item
Retrieve metadata for a driveItem in a drive
- Download Drive Item
Download the contents of a driveItem
- Update Drive Item
Update the properties of a driveItem
- Move Drive Item
Move a driveItem to a new parent item
- Delete Drive Item
Delete a driveItem
Item Versions
- List Item Versions
Retrieve the versions of a file
- Get Item Version
Retrieve metadata for a specific version of a driveItem
- Download Item Version
Download the contents of a specific version
Item Permissions
- List Item Permissions
List permissions on a driveItem
- Get Item Permission
Get a specific permission on a driveItem
- Update Item Permission
Update a permission on a driveItem
- Delete Item Permission
Remove a permission from a driveItem
Users
- Create User
Create a new user account in the organization with the specified properties
- List Users
Retrieve a list of user objects. By default, returns a limited set of properties (businessPhones, displayName, givenName, id, jobTitle, mail, mobilePhone, officeLocation, preferredLanguage, surname, userPrincipalName). Use $select to specify alternative properties.
- Get User
Retrieve the properties and relationships of a specific user by their ID or userPrincipalName. By default, only a limited set of properties are returned (businessPhones, displayName, givenName, id, jobTitle, mail, mobilePhone, officeLocation, preferredLanguage, surname, userPrincipalName). Use the select parameter to return an alternative property set.
Other (20)
- Create Folder
Create a new folder in a drive
- Upload File To Drive
Upload a new file to a drive location
- Create Sharing Link
Create a sharing link for a driveItem
- Send Sharing Invitation
Send a sharing invitation to users
- List Current User's Drives
Retrieve the list of drive resources available for the authenticated user
- List User's Drives
Retrieve the list of drive resources available for a specific user
- Get Drive
Get metadata about a specific drive
- Get Default Drive
Get the user's default OneDrive
- Get Drive Root Folder
Get the root folder of a drive
- List Drive Root Children
List children of the root folder of a drive
- List Followed Items
List items the user is following
- Get Special Folder
Access a special folder by its canonical name
- List Drive Item Children
List children of a driveItem
- Get Drive Item By Path
Retrieve a driveItem by file system path
- Get Drive Item Thumbnails
List thumbnails for a driveItem
- Follow Drive Item
Follow a driveItem
- Unfollow Drive Item
Unfollow a driveItem
- Restore Drive Item
Restore a deleted driveItem from the recycle bin
- Check In Drive Item
Check in a checked out driveItem
- Check Out Drive Item
Check out a driveItem
Set Up Your Microsoft OneDrive MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Microsoft OneDrive in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}More Cloud Storage MCP Servers
Box
83+ actions
Dropbox
82+ actions
Google Drive
47+ actions
SharePoint
19+ actions
Azure Blob Storage
2+ actions
Microsoft OneDrive MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Microsoft OneDrive MCP Server FAQ
Microsoft OneDrive MCP server vs direct API integration — what's the difference?
A Microsoft OneDrive MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Microsoft OneDrive. A Microsoft OneDrive MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Microsoft OneDrive at runtime. StackOne provides both.
How does Microsoft OneDrive authentication work for AI agents?
Microsoft OneDrive authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Microsoft OneDrive account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Microsoft OneDrive MCP tools vulnerable to prompt injection?
Yes — Microsoft OneDrive MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Microsoft OneDrive agent and how do I avoid it?
Context bloat happens when Microsoft OneDrive tool schemas and API responses eat your Microsoft OneDrive agent's memory, preventing it from reasoning effectively. A single Microsoft OneDrive query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Microsoft OneDrive agent can access?
Yes — you can limit which actions your Microsoft OneDrive agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Microsoft OneDrive MCP server?
Yes — you can create custom agent actions for your Microsoft OneDrive MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Microsoft OneDrive's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Microsoft OneDrive MCP server?
Skip a Microsoft OneDrive MCP server if your integration is purely software-to-software — direct Microsoft OneDrive API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Microsoft OneDrive actions at runtime.
What AI frameworks and AI clients does the StackOne Microsoft OneDrive MCP server support?
The StackOne Microsoft OneDrive MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.