How is this different from connecting Outlook MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Outlook MCP API changes?

We track the Outlook MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Outlook tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Outlook?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Outlook MCP server myself?

No. TrustGate connects to the Outlook MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Outlook directly.

Connect Outlook MCP to your AI agents, securely.

Q: Is Outlook MCP secure?

The server itself exposes 10 tools, and some of them can write to your Outlook account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Outlook.

One secured endpoint for every Outlook call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Outlook MCP now

What your agents can ask once Outlook MCP is connected.

Select the tools your AI agents can call

10 tools from the Outlook MCP schema.

Showing 10 tools

mcp_MailTools_graph_mail_createMessagewriteCreate a draft email. Supports HTML by setting body.body.contentType to HTML.
mcp_MailTools_graph_mail_sendMailwriteSend an email as the signed-in user.
mcp_MailTools_graph_mail_sendDraftwriteSend an existing draft message by ID.
mcp_MailTools_graph_mail_getMessagereadGets a message by ID from the signed-in user's mailbox.
mcp_MailTools_graph_mail_updateMessagewriteUpdates a message's mutable properties, such as the subject, body, and categories.
mcp_MailTools_graph_mail_deleteMessagehigh riskDeletes a message from the signed-in user's mailbox.
mcp_MailTools_graph_mail_replywriteSend a reply to an existing message. Supports HTML via preferHtml or headers.
mcp_MailTools_graph_mail_replyAllwriteSend a reply-all to an existing message. Supports HTML via preferHtml or headers.
mcp_MailTools_graph_mail_searchMessagesreadSearch Outlook messages using the Microsoft Graph Search API with KQL style queries.
mcp_MailTools_graph_mail_listSentreadList messages in sent items.

What Outlook MCP exposes

Outlook MCP groups its 10 tools into 4 categories, each with a suggested starting policy.

All 10 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Compose	Draft creation, sending mail and sending existing drafts	Read / Write	Require approval before sending
Messages	Message retrieval, updates and deletion	Read / Write	Require approval before deleting mail
Replies	Reply and reply-all on an existing message	Read / Write	Require approval before sending
Search	KQL search across messages and listing sent items	Read	Limit to the connected mailbox

Connect Outlook MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Outlook
Find Outlook in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Outlook MCP or block it. You allow the exact tools each agent can call, one by one.

Outlook MCP	10 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 10 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Outlook MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Outlook MCP10 documented tools.
Coding assistants	Connection & credentialsper user	Compose3 tools
Internal copilots	Tool access policiesdeny by default	Messages3 tools
Workflow automations	Request & response inspectioninline	Replies2 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools2 tools