Posts Tagged: Claude

Introducing the MIDAS MCP Server: Manage Your Bookings With Any AI Assistant

6 minute read time · Updated July 8, 2026 · First published July 8, 2026
MIDAS MCP Server

Booking and scheduling should be quick. Yet checking whether a room is free, adding a booking, or pulling up next week’s schedule still usually means logging in, clicking through menus, and filling in forms. What if you could simply ask?

We are pleased to announce the new MIDAS MCP Server add-on, which lets you connect your MIDAS room and resource booking system directly to the AI assistant of your choice, including Claude, ChatGPT, and Google Gemini. Once connected, you can check availability, add and amend bookings, look up clients, manage resources, and even raise invoices, all through natural conversation.

What is an MCP server?

MCP stands for Model Context Protocol. It is an open standard that lets AI assistants connect securely to other software and data sources. On its own, an AI assistant has no way to look things up in your systems or carry out actions in them. An MCP server bridges that gap. It exposes a defined set of “tools” that an AI assistant is allowed to use, so the assistant can read information from a connected system and, where permitted, make changes to it too.

Because MCP is an open standard, any AI platform that supports it can connect to a compatible MCP server. That means the MIDAS MCP Server is not tied to a single AI provider. You choose the assistant you already use and prefer, and connect it to MIDAS.

Book and manage rooms using plain English

Once the MIDAS MCP Server is enabled and connected to your AI assistant, everyday booking tasks become as simple as asking a question. For example, you could say:

  • “Is the Boardroom free tomorrow afternoon?”
  • “Book Studio 1 from 2pm to 4pm on Friday for a client meeting.”
  • “Show me all bookings for Meeting Room 3 next week.”
  • “Which rooms are available on Thursday morning for 20 people?”
  • “Generate an invoice for last month’s confirmed bookings for Acme Ltd.”
  • “Who is the client with the email address [email protected]?”

Your AI assistant translates each request into the appropriate action, sends it to MIDAS, and replies in plain English. There are no menus to navigate and no forms to complete for these routine tasks.

A booking and scheduling system that works with your AI agent

If you have been searching for a booking, scheduling, or calendar system that integrates with your chosen AI agent or platform, the MIDAS MCP Server is designed for exactly that. It turns MIDAS into a fully AI-accessible booking system, without locking you into any one AI provider.

This opens the door to more than just chat. Because any MCP-compatible AI assistant or agent can connect, you can build assistants and automations around your booking data. Think of a front-of-house assistant that answers availability enquiries, or an agent that drafts invoices from the week’s confirmed bookings. If a platform supports MCP, it can work with MIDAS.

Availability

The MIDAS MCP Server is an optional add-on available from MIDAS v4.43 (or later). It’s available for both cloud-hosted an self-hosted editions of our booking system.

Existing customers (running MIDAS v4.43 or later) can add the MCP Server add-on to their system via mid.as/upgrade.

New customers can obtain MIDAS with the optional MCP Server add-on via mid.as/pricing.

Which AI platforms are supported?

The MIDAS MCP Server works with any AI assistant or platform that supports the Model Context Protocol, including:

  • Claude (Anthropic), via both Claude Desktop and the Claude web and mobile apps.
  • ChatGPT (OpenAI), via its Connectors feature.
  • Google Gemini, via the Gemini CLI.
  • Other MCP-compatible platforms, including a growing range of AI-powered tools and agent platforms.

Support for MCP is expanding quickly across the AI industry, so the list of compatible platforms continues to grow.

Built with security and control in mind

Giving an AI assistant access to your booking system is a significant step, so our MIDAS MCP Server puts you firmly in control:

  • Read-only mode – Start by allowing enquiries and availability checks only. The AI can look things up but cannot change anything. Enable write access later, when you are ready.
  • Secure by default – Connections require HTTPS and are protected by a confidential MCP key that you generate and can revoke at any time.
  • IP restrictions – Optionally limit access to specific IP addresses.
  • Your existing rules still apply – Every action taken through the MCP server respects the same permissions and business rules that already govern your MIDAS system. You can even configure the MCP to inherit the permissions of a specific user account.
  • A clear activity trail – Actions taken through the MCP server can be recorded in your MIDAS Recent Activity log, so you can see what was done.

Everything you can do

The MIDAS MCP Server provides a comprehensive set of tools covering the full range of day-to-day booking and administration tasks, including:

  • Checking venue and resource availability
  • Adding, amending, deleting, and restoring bookings
  • Approving and rejecting pending booking requests
  • Looking up and managing clients
  • Managing venues, venue groups, and bookable resources
  • Checking consumable stock levels
  • Raising, amending, and generating invoices
  • Sending notifications and emailing clients
Some of the tools available in the MIDAS MCP Server (shown here in Claude Desktop)
Some of the tools available in the MIDAS MCP Server (shown here in Claude Desktop)

Read-only tools retrieve information only, while write tools can create and change data. If you run the server in read-only mode, only the read-only tools will be available.

Getting started

Setting up the MIDAS MCP Server takes just a few minutes:

  1. Get the MCP Server addon (mid.as/upgrade for existing customers, mid.as/pricing for new customers)
  2. Enable the MCP Server addon and connect your AI assistant (here’s how)
  3. Start asking your AI assistant about your bookings.

Full instructions for each supported platform, including Claude, ChatGPT, and Gemini, are available in our documentation.

Read the MIDAS MCP Server documentation and get started ยป

The future of booking is conversational

AI assistants are quickly becoming part of everyday working life. With the MIDAS MCP Server, your booking and scheduling system is ready to be part of that shift. Whether you want to check availability at a glance, speed up routine admin, or build richer automations around your booking data, the MIDAS MCP Server connects MIDAS to the AI tools you already use.

Existing MIDAS customers can find out more and get set up today on our MIDAS MCP Server pages. New to MIDAS? Discover why MIDAS is the flexible, affordable choice for room and resource booking, now with AI built in.

Tags: , , , , , , ,

Why We’ve Switched from OpenAI to Claude

5 minute read time · Updated March 5, 2026 · First published March 5, 2026
OpenAI vs Claude AI

Over the past week, a significant and fast-moving controversy has unfolded in the AI industry – one that has caused us, along with many others, to take a hard look at which AI companies we choose to support and partner with.

We’ve decided to switch. From today, MIDAS is moving away from OpenAI and over to Claude, the AI assistant developed by Anthropic.

Here’s why.

What Happened

If you haven’t been following the news, here’s a quick summary. The US Department of Defense had been using Anthropic’s Claude AI on its classified networks – the first AI to be deployed in that context. As the contract came up for renegotiation, the Pentagon demanded that Anthropic remove two key restrictions from the agreement: a prohibition on using Claude to power fully autonomous weapons systems, and a prohibition on using it for mass domestic surveillance of American citizens.

Anthropic refused. Their CEO, Dario Amodei, was unequivocal: current AI models are simply not reliable enough to be trusted with lethal autonomous targeting decisions, and mass surveillance of citizens is incompatible with democratic values. The company had tried for months to reach a workable agreement, but the Pentagon’s position was that it required the ability to use AI for “all lawful purposes” without restriction – a standard that, as legal experts have noted, is far broader than it sounds.

The fallout was swift. President Trump ordered every federal agency to immediately cease using Anthropic’s technology. Defense Secretary Pete Hegseth announced Anthropic would be designated a national security supply chain risk. Hours later, OpenAI – having apparently been in talks throughout – announced it had struck a deal with the Pentagon to fill the gap.

Many of OpenAI’s own employees were furious. A number of them, along with other prominent tech figures, signed an open letter opposing the government’s retaliation against Anthropic. Sam Altman himself had written in an internal memo just days earlier that OpenAI shared Anthropic’s “red lines” – before going on to sign a deal that critics said those red lines were far less robustly protected.

The contrast in the two companies’ behaviour was stark and, for us, clarifying.

Why This Matters to Us

We’re a small UK software company. We make room booking software. We’re not in the defence industry, and the intricacies of US military contracting aren’t something we’d normally have strong opinions about.

But this issue isn’t really about US military contracts. It’s about what kind of company you’re doing business with – what they stand for, and what they’re willing to sacrifice to stay in favour with those in power.

Anthropic chose to walk away from a government contract worth up to $200 million rather than remove safeguards they believed were ethically essential. OpenAI, in the same week its CEO had privately affirmed those same values to his own staff, made the opposite choice.

We think that matters. The companies whose technology we choose to use reflect, in a small way, on us. And we’d rather reflect the values of a company that held its ground.

What We’ve Changed

We used OpenAI’s models primarily in two places within our products and workflows:

Miriam, our virtual assistant. When no live support agents are available, visitors to our website can get help from Miriam, our AI-powered chatbot. Miriam was previously powered by OpenAI. She’s now powered by Claude.

Code optimisation. As we written about previously, we’ve been using AI assistance to help our human developers optimise MIDAS source code – identifying opportunities to make our software run faster and more efficiently. We’ve switched that workflow from ChatGPT to Claude as well.

In both cases, the transition has been smooth. Claude is a highly capable model, and we’re pleased with the results so far.

We’re Not Alone

Claude surged to number one on the Apple App Store in the days following the controversy. Thousands of individuals and organisations made the same decision we did – not because Anthropic asked them to, but because the situation made the choice feel important.

It’s worth noting that this isn’t simply about picking a “winner” in a commercial rivalry. We genuinely hope the situation with Anthropic and the US government is resolved fairly and without further retaliation. Anthropic has, by all accounts, been one of the most thoughtful voices in AI development when it comes to safety and responsible deployment. The idea of that voice being sidelined – or punished for speaking up – should concern anyone who cares about where this technology is heading.

A Note on AI in MIDAS

As we’ve said before, AI is not taking over the development of MIDAS. Our software is, and will remain, built and maintained by our human team. But AI tools have become a genuinely useful part of how we work – and it matters to us that we use them thoughtfully, including being selective about whose tools we use and why.

If you have any questions about these changes, or about how AI is used in our products, please don’t hesitate to get in touch.

Tags: , , , , ,