Connect
Optimize
Secure
Microsoft Outlook MCP Server
for AI Agents
Production-ready Microsoft Outlook MCP server with 39 extensible actions — plus built-in authentication, security, and optimized execution.
Microsoft Outlook MCP Server
Built by 
StackOne
StackOne 
Coverage
39 Agent Actions
Create, read, update, and delete across Microsoft Outlook — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Microsoft Outlook MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Microsoft Outlook 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 Outlook call.
Tools Discovery →What is the Microsoft Outlook MCP Server?
A Microsoft Outlook MCP server lets AI agents read and write Microsoft Outlook data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Microsoft Outlook MCP server ships with 39 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 Outlook MCP Tools and Actions
Every action from Microsoft Outlook's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Messages
- Copy Message
Copy a message to a destination folder
- List Messages
Get all messages in the signed-in user's mailbox or in a specific folder
- Get Message
Read properties and relationships of a specific message
- Update Message
Update the properties of a message object
- Move Message
Move a message to a destination folder
- Delete Message
Delete a message in the user's mailbox
Draft Messages
- Create Draft Message
Create a draft of a new message in JSON format
- Send Draft Message
Send a previously created draft message
Attachments
- Add Attachment
Add a file, item, or link attachment to a message
- List Attachments
Retrieve a list of attachments attached to a message
- Get Attachment
Get the properties and relationships of an attachment
- Delete Attachment
Delete an attachment from a message
Mail Folders
- Create Mail Folder
Create a new mail folder in the root folder
- Copy Mail Folder
Copy a mailFolder and its contents to another mailFolder
- List Mail Folders
Get the mail folder collection under the root folder
- Get Mail Folder
Retrieve properties and relationships of a mail folder
- Update Mail Folder
Update the writable properties of a mailFolder object
- Move Mail Folder
Move a mailFolder and its contents to another mailFolder
- Delete Mail Folder
Delete a mail folder
Child Folders
- Create Child Folder
Create a new child mail folder under a specified folder
- List Child Folders
Get the folder collection under the specified folder
Message Rules
- Create Message Rule
Create a message rule with conditions and actions
- List Message Rules
Get all message rules defined for the user's inbox
- Get Message Rule
Read properties and relationships of a message rule
- Update Message Rule
Change writable properties of a message rule
- Delete Message Rule
Delete a message rule
Other (13)
- Send Mail
Send a new email message using JSON or MIME format
- Create Draft Reply To Message
Create a draft to reply to the sender of a message
- Create Draft Reply All To Message
Create a draft to reply to the sender and all recipients of a message
- Create Draft To Forward Message
Create a draft to forward an existing message
- Create Message In Mail Folder
Create a new draft message in a specified mail folder
- Get Message Delta From Folder
Get a set of messages added, deleted, or updated in a specified folder
- Get Mail Folder Delta
Get incremental changes to mail folders in the mailbox
- List Folder Messages
Get all messages in a specified folder
- Forward Message
Forward a message to specified recipients
- Reply To Message
Reply to the sender of a message
- Reply All To Message
Reply to all recipients of a message
- Permanently Delete Message
Permanently delete a message and place it in the purges folder
- Permanently Delete Mail Folder
Permanently delete a mail folder and remove its items from the mailbox
Set Up Your Microsoft Outlook MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Microsoft Outlook 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>"
]
}
}
}Microsoft Outlook 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 Outlook MCP Server FAQ
Microsoft Outlook MCP server vs direct API integration — what's the difference?
A Microsoft Outlook MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Microsoft Outlook. A Microsoft Outlook 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 Outlook at runtime. StackOne provides both.
How does Microsoft Outlook authentication work for AI agents?
Microsoft Outlook 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 Outlook account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Microsoft Outlook MCP tools vulnerable to prompt injection?
Yes — Microsoft Outlook 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 Outlook agent and how do I avoid it?
Context bloat happens when Microsoft Outlook tool schemas and API responses eat your Microsoft Outlook agent's memory, preventing it from reasoning effectively. A single Microsoft Outlook 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 Outlook agent can access?
Yes — you can limit which actions your Microsoft Outlook 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 Outlook MCP server?
Yes — you can create custom agent actions for your Microsoft Outlook MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Microsoft Outlook's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Microsoft Outlook MCP server?
Skip a Microsoft Outlook MCP server if your integration is purely software-to-software — direct Microsoft Outlook 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 Outlook actions at runtime.
What AI frameworks and AI clients does the StackOne Microsoft Outlook MCP server support?
The StackOne Microsoft Outlook 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.