Guide

Can Claude read my email? Yes, four ways.

Claude can read, search and answer email, and which mailbox it can reach, and what it can do once it is in, depends on which of four routes you take. Three are Anthropic's own. The fourth is the one that reaches everything else, and it is what this site sells, so every claim about it here was measured rather than promised.

  • Reading About 11 minutes
  • Routes 4, and one is ours
  • Vendor pages read 11 September 2026

The short version

Yes. Claude reads and searches a Gmail or work Microsoft 365 mailbox through Anthropic's own connectors, and reads the message you have open through its Outlook add-in. It sends on two of those routes and files on none of them. A custom connector such as Mailbox MCP is how Claude reaches any other mailbox, including a personal outlook.com address or any IMAP host, and how it moves, flags and files what it reads. On every route it acts when you ask, not on its own.

The map

The four ways Claude can reach a mailbox

"Can Claude read my emails" gets four different answers depending on which Claude product is doing the reading, and most pages that answer it describe one of the four as if it were the whole story. Anthropic runs three separate mail integrations, on different plans, with different capabilities, and the fourth route is a connector somebody else built, which is what we build. The table is the whole guide in one glance; the sections after it are the evidence for each cell.

  Gmail connector Microsoft 365 connector Outlook add-in Mailbox MCP (custom)
Which mailboxes Google accounts Work Microsoft 365, not personal outlook.com Exchange Online through Microsoft 365 Gmail, work or personal Microsoft, any IMAP host
Claude plan Stated two ways, see below All plans Pro, Max, Team, Enterprise All plans, one connector on Free
Reads and searches Yes Yes The open message, plus search Yes, without marking anything read
Sends Yes, asks first by default Yes, once an admin enables writes Never. Drafts land unsent Yes, and asks first in your client
Sends with an attachment Not stated Refused on every write Not applicable Yes, up to 10 MB
Moves to a folder, flags, marks read Not stated No such tools published Move and flag, via Graph Yes, all three

Every vendor cell was read from the page cited under it on . "Not stated" means the vendor's page neither confirms nor denies it, which is a different thing from "no", and the difference matters on the rows that decide whether Claude can run an inbox rather than just look at one. The full six-product comparison, with Copilot and Gemini as well, is on the native connectors versus MCP page; this guide stays on Claude.

Route one

Can Claude read my Gmail? Its own connector

Yes, and this is the route most people mean. Under Customize and then Connectors, Claude offers Gmail alongside Google Calendar and Google Drive. Sign in to Google, grant the permissions, and Claude can search the mailbox in natural language, read messages and threads, and draft replies. It sends as well. Anthropic's help centre, read on , lists the capability in one line, and the second sentence is the one to notice:

Send, reply to, and forward emails from Gmail. By default, Claude asks for your approval before each of these actions.

Anthropic, Use Google Workspace connectors

That "by default" is doing real work. It means the approval is a setting rather than a guarantee, and that a conversation where it has been switched off will send without showing you the message. It is the right default and it is worth knowing it is a default. The same page lists what Claude gets about attachments, which is their metadata and, in Anthropic's words, "not attachment content": Claude can tell you there is a PDF called invoice-0412 on a message and cannot tell you what is in it.

The plan question has two answers on Anthropic's own site, and both are quoted on the comparison page: the help centre says the Google Workspace connectors are available for all users, the developer documentation names Pro, Max, Team and Enterprise. Your own Connectors screen is the only answer that counts.

What the page does not say is the part this guide keeps coming back to. The only mutation verb on it besides sending is "labels". Moving a message, trashing it, flagging it, marking it read: none of those appears anywhere on the page, so whether Claude can do them through this connector is not stated, and a reader who wants Claude to tidy a Gmail inbox rather than search it has no documented basis for expecting that it can.

Whether Claude can read your email depends on the route: the robot inside a screen with both hands pressed against it, and a mailbox standing out of reach beside it.
Reads and sends, on Google accounts, when you ask

Routes two and three

Can Claude use Outlook? Two Microsoft routes, and one mailbox neither reaches

Yes, with a sharp condition on which Outlook. Anthropic's Microsoft 365 connector is available on every Claude plan including Free, and it connects a work or school mailbox: in the set-up article's own words, it "requires a Microsoft Entra tenant tied to a Microsoft Business plan", and "Personal Microsoft accounts (such as @outlook.com or @hotmail.com addresses) can't be used to connect." So the Outlook most people have at home, the free one on outlook.com, is exactly the one Anthropic's connector refuses.

On a work mailbox it reads everything, and writing is switched on by an administrator. Anthropic publishes the connector's full tool list, which is the most checkable capability evidence any vendor gives, and the list sends, forwards, drafts, trashes and applies categories. Its security guide, read the same day, also states that every write tool rejects a message carrying an attachment, and that sent mail carries a marker:

Emails Claude sends include an attribution header identifying them as agent-initiated.

Anthropic, Microsoft 365 connector security guide

Read that beside the founding rule of this product, which is that a recipient should not be able to tell a message was handled by an assistant, and you have the clearest statement of the difference between the two designs. Anthropic's connector labels the mail; ours threads it, files one copy in Sent and leaves nothing else behind. Neither is wrong. They are answers to different questions, and it is better to know which one you are buying.

The third route is Claude for Outlook, an add-in that puts Claude inside the Outlook window on Pro, Max, Team and Enterprise. It reads the open message and its Word and Excel attachments, searches the mailbox, and, unusually, moves and flags messages through Microsoft Graph. What it never does is send, in the words of its own documentation, read the same day:

Claude never sends mail or invites on its own. The add-in does not request the Mail.Send permission. Every draft lands unsent in Outlook's compose or appointment form, and you click Send.

Anthropic, Use Claude for Outlook

That is the most useful sentence any vendor has published about an assistant and a mailbox, because it names the permission rather than the intention. A product that has not been granted Mail.Send cannot send, whatever a prompt or a hidden instruction in an incoming message asks it to. If what you want is Claude drafting inside Outlook and you pressing every Send yourself, this route is the right one and this guide has nothing to sell you.

Which Outlook Claude can use: the robot turning away a password card at a padlocked mailbox and holding up a sign-in badge instead.
Work mailboxes on two routes. Home ones on a fourth

A personal outlook.com mailbox connects here with the same single Microsoft sign-in, on the free tier, with no card.

The gap

Can Claude manage my inbox? What none of Anthropic's three routes do

Managing an inbox means filing, not just finding. Put the three routes side by side and the same gaps appear in each, and they are gaps in the vendor's own documentation rather than in anybody's opinion of it.

None of the three publishes a tool that moves a message to a folder. The Gmail page says "labels" and nothing about moving. The Microsoft 365 tool list has trash and untrash, which move to Deleted Items and back, and no move tool at all, on a page whose permission description says the scope covers moving. The add-in moves, but only as part of an action you take on an open message in Outlook. So through Claude's own connectors, Claude can find the forty messages that belong in a project folder and cannot put them there.

Flagging and marking read are the same story. Neither appears in the Gmail article, neither is in the Microsoft 365 tool list. And on the question underneath all of this, whether Claude reading a message through any of these routes marks it as read, no vendor page we could find says anything at all. That silence is the difference between a measurement and a promise, and it decides whether a triage pass you abandon halfway leaves your unread count meaning anything.

And none of them reaches a mailbox that is not the vendor's own. Google accounts on one route, business Microsoft tenants on the other two. A Fastmail, iCloud, Zoho or cPanel mailbox, or the outlook.com address you have had since 2009, cannot be connected to Claude through anything Anthropic ships. That is not a criticism of Anthropic, who never claimed otherwise. It is the reason the fourth route exists.

  • Reading a message Does not mark it read
  • Moving a message Flags and original date kept
  • Deleting a message Moves to Trash, never expunges
  • Replies In-Reply-To and References carried
  • Copies filed per send 1, no duplicate
  • Attachment bytes SHA-256 identical on arrival

Those six rows are what "manage my inbox" turns on, measured on the fourth route against a live mailbox of 26,930 messages rather than inferred from an API response. They are the rows the vendor pages leave blank.

Route four

The fourth way: a custom connector, on the Claude plan you already have

Claude can connect to servers Anthropic did not build, through the same Connectors screen, by pasting a URL. Anthropic calls these custom connectors and the protocol they speak is MCP, which is the part of the name of this product that nobody searching "can Claude read my email" has ever typed. What matters here is the plan gate, read the same day, because it is the opposite of what people assume:

Custom connectors using remote MCP are available on Claude, Cowork, and Claude Desktop for users on free, Pro, Max, Team, and Enterprise plans. Free users are limited to one custom connector.

Anthropic help centre, custom connectors

So a free Claude account can connect one mailbox this way, and a paid one as many as it likes. The same page carries an example of what an organisation can restrict a connector to, and it happens to be our product described in reverse: "Allow Claude to search and summarize email, but prevent it from sending messages." The control sits with the Claude side, on top of whatever the connector offers.

Mailbox MCP is one such connector. You connect the mailbox to it, Gmail with an app password, Outlook or Microsoft 365 with one Microsoft sign-in, or any IMAP host with the settings you already have, and then add one URL to Claude. Claude is then handed 31 email tools, every one of them named on the tools page with what it refuses, and the mailbox behaves as the ledger above says it does. The mailboxes this product was built against are the author's own, and they are connected to Claude through it as this is written.

The obvious question is what it costs on top of Claude, and the answer is stated once, everywhere: 5 calls a day on any mailbox for nothing, and £2.92 a month per mailbox, paid annually at £34.99 + VAT, for 1,000. There is no second AI subscription in that: it uses the Claude you already pay for, or the free one.

A custom connector reaching any mailbox from Claude: the robot feeding one cable out to four different screens running different assistants.
One URL in the Connectors screen. Any mailbox behind it

Balance

When Claude's own connector is enough

A page from the company selling the fourth route should say plainly when the first three are the better choice, so here it is.

If your mail is in Gmail and what you want is search, summaries and the occasional reply, Anthropic's Gmail connector does that, is a single sign-in with no app password, and asks before it sends. Try it first. This page's honest advice is the same as the comparison page's: use the built-in one until you hit something it will not do.

If you are on a work Microsoft 365 mailbox and your organisation has approved Claude, the Microsoft 365 connector reads everything on every plan, and the Outlook add-in is the safest drafting assistant any vendor ships, because it cannot send. Either is the right answer for a reader whose IT department would rather Claude never held Mail.Send at all.

You want the fourth route when the mailbox is on a provider Anthropic does not connect, including a personal outlook.com address; when you want Claude to file, flag and mark as well as read; when a reply has to land inside the thread it belongs to and file one copy in Sent; when an attachment has to go with the message; or when you would rather reading a message left it unread. Each of those is a row in the table at the top, and each is the reason a particular customer came here.

Choosing between Claude's own mail connector and a custom one: the robot under a signpost pointing one way to a sign-in and the other to a server address.
Built-in first. The fourth route when it stops

If you have already hit one of those rows, the free tier is enough to check the fourth route on a mailbox you do not mind.

Limits

What this guide cannot tell you

  • Tomorrow's Anthropic

    Whether Anthropic's connectors still do what its pages said on 11 September 2026. They change monthly, the plan gates move, and the dates on every quotation here are there so you can tell how old a claim is.

  • The unread flag, on their routes

    Whether reading through Anthropic's own connectors marks a message read. No vendor page says. We measured our own route and say so; we cannot measure theirs for you.

  • Anything unattended

    Whether Claude can watch an inbox and act as mail arrives. On none of the four routes here does anything run without a conversation you started. This product has no scheduler, by design, and says so.

  • Your employer's rules

    Whether your organisation permits any of it. On a work mailbox an administrator decides, and on the Microsoft 365 connector Anthropic gives them the switch for writes.

Can Claude read my emails?

Yes. Claude reads and searches a Gmail mailbox through Anthropic's own Gmail connector, a work Microsoft 365 mailbox through its Microsoft 365 connector, and the message you have open in Outlook through the Claude for Outlook add-in. It reads a mailbox on any other provider, including a personal outlook.com address or any IMAP host, through a custom connector such as Mailbox MCP. In every case it reads when you ask, inside a conversation, and not on its own in the background.

Can Claude send emails for me?

Yes, on three of the four routes. Anthropic's Gmail connector sends, replies and forwards, and by default asks for your approval before each one. The Microsoft 365 connector sends too, once an administrator has enabled its write tools, and rejects any message with an attachment. The Outlook add-in never sends: every draft lands unsent in Outlook for you to press Send. Through a custom connector like this one Claude sends from any connected mailbox, with attachments up to 10 MB, files exactly one copy in Sent, and threads the reply so it lands inside the original conversation.

Can Claude use Outlook?

Yes, and which route depends on which Outlook you mean. A work or school Microsoft 365 mailbox connects through Anthropic's Microsoft 365 connector on any Claude plan, or through the Outlook add-in on a paid plan, or through a custom connector. A personal outlook.com or hotmail.com address is refused by Anthropic's own connector, in its own words, so the only route to one of those is a custom connector: Mailbox MCP connects it with a single Microsoft sign-in.

Can Claude manage my inbox?

It can read, sort and act on a mailbox when you ask it to, which is inbox management in the sense most people mean. What decides how far it gets is the route: Anthropic's connectors publish no tool for moving a message to a folder, flagging it or marking it read, so Claude can find and answer mail through them but cannot file it. A custom connector like this one gives Claude 31 email tools including move, flag, mark read and unread, archive and junk, so it can work through a full inbox and leave it filed. No route runs while you are away: there is no rule or trigger, so "manage" means when you ask, not around the clock.

Which Claude plan do I need to connect my email?

For a custom connector such as Mailbox MCP, any plan: Anthropic states that custom connectors using remote MCP are available on free, Pro, Max, Team and Enterprise plans, with free accounts limited to one custom connector. Anthropic's own Microsoft 365 connector is on all plans as well. Its Gmail connector is described as available for all users in the help centre and as Pro, Max, Team and Enterprise in the developer documentation, and the Outlook add-in is Pro, Max, Team and Enterprise. Check your own Connectors screen rather than trusting any table, including this one, because the gates move.

Does Claude reading a message mark it as read?

Through Mailbox MCP, no: the engine fetches with IMAP's BODY.PEEK, which leaves the unread flag exactly as it was, and marking a message read is a separate tool that runs only when you ask. Through Anthropic's own connectors, nobody knows, because no vendor page we could find says either way. That silence is the difference between a measurement and a promise, and it is worth checking on a message you do not mind before you trust either.

Can Claude read my email attachments?

Anthropic's Gmail connector gives Claude attachment metadata and, in its own words, not attachment content. The Outlook add-in reads Word and Excel attachments on the open message inline. Mailbox MCP does not pass attachment bytes through the conversation either; instead every attachment comes back with a short-lived download link, so Claude can hand you the file, and can attach the same file to a new message without ever reading it.

Attribution

Sources

Keep going

Read next

Can ChatGPT read my email? Yes, on a paid plan, and here is where it stops

ChatGPT reads Gmail and Outlook once they are connected, and has sent email since June 2026. What OpenAI documents it doing to your own mailbox, what it leaves unstated, and the MCP route that covers the rest.

Is it safe to give an AI access to your email?

It depends on the connector, not on the AI. Eight questions worth putting to any vendor before you connect a mailbox, with our own answers to all eight, in full.

Can an AI manage my inbox? Triaging a full inbox without losing anything

Read-only first, decide in batches, act last. The method leans on one property of the engine: reading a message does not mark it read, so a triage pass you abandon halfway leaves no trace.

Connect the mailbox Claude cannot reach on its own.

A personal Outlook, an IMAP host, or a Gmail you want filed rather than searched. 5 calls a day, no card, and one URL in Claude's Connectors screen.