Skip to main content
All connectors
qbash Connectors / Outlook Mail

Outlook Mail MCP serverand Python AI tasks

qbash hosts a Outlook Mail MCP server you can use in Claude, ChatGPT, Codex, Cursor, Grok Bot and Muse.

Developers use qbash Tasks to write cloud-hosted Python functions that pair Outlook Mail with models such as Claude and GPT.

MCP server

Build a Outlook Mail MCP server

Give ChatGPT, Claude and your other AI tools access to Outlook Mail through one server. You pick which Outlook Mail tools it shares, and you can add other connectors, memory folders and Tasks to the same server.

How to set it up

  1. Connect Outlook Mail on the qbash Connectors page.
  2. Create an MCP server and add the Outlook Mail tools you want to share.
  3. Paste the server URL into your client. It connects with OAuth or an access token.

Python AI task

Write a Outlook Mail task in Python

A qbash Task is a hosted Python function that calls Outlook Mail and AI models.

Triage unread messages with attachments

Read unread inbox messages that have attachments, then ask an inline prompt to sort them into a review queue by sender and request.

main.py
report = qbash.integrations.outlook_mail.list_messages(
folder_id="inbox",
read_status="unread",
has_attachments="with",
top=25,
skip=0,
)
messages = report.get("value", [])
if messages:
queue = qbash.ai.run_prompt(
slug="outlook-attachment-queue",
variables={"messages": json.dumps(messages)},
)
qbash.output({"queue": queue, "more_available": bool(report.get("@odata.nextLink"))})
else:
qbash.output("No unread messages with attachments were returned.")
Sample list_messages response
{
"value": [
{
"id": "message-123",
"subject": "September invoice",
"from": {
"emailAddress": {
"address": "billing@example.com"
}
},
"receivedDateTime": "2026-09-29T10:00:00Z",
"hasAttachments": true,
"isRead": false,
"bodyPreview": "Please find the invoice attached."
}
]
}

What the Outlook Mail connector can do

  • Get a specific Outlook message by ID
  • List messages in the user's Outlook mailbox
  • Send an email via Outlook
  • Create a draft email in Outlook
  • Delete an Outlook message by ID
  • Download an attachment from an Outlook message
  • List attachments on an Outlook message
  • Move an Outlook message to a different folder
  • Mark an Outlook message as read or unread
  • Update properties of an Outlook message
  • List available Outlook message categories
  • List mail folders in the user's Outlook mailbox
  • Get initial delta state for tracking Outlook message changes
  • Poll for Outlook message changes using a delta link
See every Outlook Mail method in the SDK Reference

qbash Tasks: AI applications in Python

A Task is a Python function that calls Outlook Mail, your other connectors and models such as Claude, GPT, Gemini and Grok. qbash hosts and runs it.

AnthropicOpenAIGeminixAI

Run Tasks on a schedule or from your team's tools

OpenAIAnthropicGrokGmailSlackGitHub+ more
  • Deterministic where it counts Write the logic in Python and call a model only for the steps that need judgement, so the rest runs the same way every time.
  • Version controlled Every save is a revision you can compare and roll back.
  • Logged Each run records its inputs, output, errors and what started it.
  • Shared credentials Connections belong to your organization, so a Task keeps working when its author is away.

Outlook Mail MCP questions

Can the Outlook Mail MCP server send email?

Yes. send_message sends from the signed-in mailbox, and create_draft saves a message for you to review in Outlook. Leave the send tool off the server if a client should only draft.

Which Microsoft permissions does it request?

Mail read, mail write and mail send, plus basic user profile access. One connection covers the single mailbox that signed in.

Build a Outlook Mail task

Write it in Python with AI steps, and qbash hosts it with versions and run logs.

Build a task

Build a Outlook Mail MCP server

Pick the Outlook Mail tools to share and connect ChatGPT, Claude or Grok Bot.

Build an MCP server