Review scheduled commitments
The assistant reads the events within a given time range and summarises them.
Example “What do I have on Thursday afternoon?” — the assistant lists the afternoon events with time, title and attendees.
The MCP (Model Context Protocol) server that lets an AI assistant read and manage a user’s schedule, integrating with Google Calendar.
LML MCP Connector is an MCP server. The Model Context Protocol is an open standard through which an AI assistant connects to external tools in order to carry out concrete operations on behalf of the person using it.
The connector exposes a narrow set of calendar operations to the assistant: reading events already scheduled, checking when time is free, creating a new appointment, updating an existing one. Those operations run on Google Calendar, subject to the user’s explicit authorisation.
It has no interface of its own: it is used through the AI assistant already deployed at the company. Every operation starts from a user request; the connector takes no action on its own initiative and does not run in the background.
Client companies of LML Technologies that already use AI assistants in their workflows and want those assistants to read and update the calendar, rather than merely suggesting what to do.
This is not a consumer product: it is activated as part of a contractual relationship with LML Technologies.
Four operations, every one of them triggered by an explicit user request.
The assistant reads the events within a given time range and summarises them.
Example “What do I have on Thursday afternoon?” — the assistant lists the afternoon events with time, title and attendees.
The assistant compares existing commitments and identifies the slots still free.
Example “Do I have two consecutive free hours next week for the project review?” — the assistant proposes the matching slots.
The assistant adds a new appointment to the calendar chosen by the user.
Example “Book a call with the supplier on Tuesday at 3 p.m., one hour.” — the event is created with title, time and description.
The assistant updates an existing event: time, duration, title, description.
Example “Move tomorrow’s meeting from 10 to 11.30.” — the event is updated to the new time.
On first use the user authorises the connector through Google. Four permissions are requested: two concern the calendar, two serve only to recognise which account is connected and give access to no content. None is broader than necessary.
https://www.googleapis.com/auth/calendar.calendarlist.readonly
https://www.googleapis.com/auth/calendar.events
https://www.googleapis.com/auth/userinfo.email
openid
The connector does not access the mailbox, contacts, files or any other service on the account. Calendar data is used solely to carry out the user’s request: it is not sold, not disclosed to third parties for their own purposes, not used for advertising, and not used to train artificial intelligence models.
The client’s administrator connects LML MCP Connector to the company AI assistant.
On first use the user authorises access from the Google consent screen and selects the account. Without this step the connector can neither read nor write anything.
The user indicates which of their calendars the connector should operate on.
Authorisation can be revoked at any time, without going through LML Technologies, from the Google account permissions page:
https://myaccount.google.com/permissionsFrom that moment the connector has no further access to the calendar. To have any residual data deleted, write to info@lmltech.it.
LML MCP Connector is an independent product of LML Technologies S.r.l. It is not sponsored, endorsed, certified by, or otherwise affiliated with Google LLC. Google Calendar is a trademark of Google LLC; the reference is purely descriptive of the technical integration.
The privacy policy sets out which data is processed, for which purposes, for how long, and how to exercise your rights.
Privacy policyhttps://lmltech.it/mcp-google/privacy