This piece was originally commissioned by and published in Dutch at Villamedia, June 24, 2026
Political editor Hans keeps hearing something has really changed in the field of AI… for the umpteenth time. New AI software such as Claude Cowork, OpenAI’s Codex, and MCP servers are said to be true game changers because they connect digital services, can program functioning apps on their own, and automate tedious workflows. This is what he said to me: “I already struggle to get ‘ordinary’ chatbots to do what I want. Help me, Laurens: do I have to delve into this?”
During one of many journalism panels on AI that I attended this year—this time at the International Journalism Festival in Perugia—moderator David Caswell and his panelists used a particular acronym nine times. That three-letter-acronym is new to many people in the room—probably to you too: MCP. My teacher’s heart always bleeds a little when a speaker assumes certain prior knowledge but loses the attention of a group in doing so.
After the reader: what comes next for news in an AI-first world? Panel session with David Casswell @ International Journalism Festival Perugia
In short, what *is* MCP?
The letters stand for Model Context Protocol. Without getting too technical, in essence, it comes down to the fact that, based on an agreed set of standardized rules, existing websites and apps can be summoned through AI chatbots. It enable users to query data and content from those apps (such as spreadsheets, documents, and images) by using natural language. You can then use your chatbot of choice to act on those answers, elaborating with follow-up questions, generating visualizations or building new apps on top of the chatbot’s output.
For journalistic applications, you could consider:
retrieve all mentioned geo-locations from the innovation section-archive, and link them to a geographical map of Europe. Or you could ask your chatbot to do the following via Good Tape, a Danish AI transcription service widely used by journalists: list all philosophical quotes from my five most recent interviews. Pay attention to references to Hannah Arendt, Kant, Popper, and Aristotle.
Another example: when analysis tools embrace MCP, you will soon be typing, “Hey chat, which user need increased our reader-conversion most, over the past nine months?” Silja, Product Marketer at Good Tape, says that their MCP (now in public beta) has changed the way she works with transcripts. “I asked Claude to turn user interviews into concrete insights. That one assignment easily saved me an afternoon.”
Panel moderator Caswell predicted that every journalist will soon be running their own em-cee-pee server. He encouraged the audience to try to take the time on some Saturday evening, pay 18 euros to Anthropic and ask Claude to assist setting up the MCP-connection of choice.
Why would you run an MCP server like this? Because it is a logical next step in the evolution of AI, Caswell and other proponents believe. After all, we have been ’talking’ to our chatbots for almost four years now. With this protocol, it is time our sites, apps, and content management systems do as well. The next step is for machines and apps to simply communicate with each other and perform tasks mutually. Then humans can step aside. For the dirty work, at least—that is the promise.
Admittedly, it sounds both frightening and promising. Caswell’s appeal convinces me. Upon returning home, I slavishly followed his call and purchased a paid Claude subscription. I read up on MCP and was ready for my experiment: going to make machines work together, under my eye!
Experiment in Lycra
To succeed, I needed three things: a goal, data, and domain knowledge. These turned out to be within reach. Tomorrow (on July 5), along with thousands of other MAMILs (Middle-Aged Men In Lycra), I will cycle 138 kilometers uphill and downhill in the Italian Dolomites. Not a very attractive idea to many; just as little for untrained amateur cyclists.
I saw it as a perfect opportunity to combine my hobby with new technology and my journalism work. A handy bonus is that Strava, the well-known running and cycling app that I already use, recently started offering such an MCP server.
Caswell is right: that very same evening I started the experiment, I manage to query my Strava data in a casual, conversational way using chatbot Claude. I easily generate a small table showing how my climbing fitness is improving. The bot has no great motivational powers, though… After I mention the dry tone, Claude’s adjusted response hasn’t improved, and it makes blunt statements that you wouldn’t accept from a meat space trainer. I am repeatedly told that I am not losing weight fast enough; after all, the fewer kilograms I carry, the easier it will be to get to the top.
What my synthetic sports coach also keeps urging me to do is a training session with at least two thousand meters of elevation gain. By comparison: the Alpe d’Huez has about eleven hundred. Admittedly, I live in the Dutch Veluwe-region, which is quite hilly for a flat country; bu travelling to mountainous territory is not an option at this point. “Have you seen my calendar, dear?” I reply. – “If you connect those, I will include that in the advice.” That I consider too dangerous from a privacy and security perspective.
Mixed results
That I manage to produce a sensible overview in natural language – without perusing boring spreadsheets, broken formulas, or complex database queries—is truly fantastic. The possibilities for new applications quickly open up in my brain. I can understand why the AI-pilled are excited. I know that this data is accurate because I’ve just generated it myself, half an hour ago, outside in a damp forest, in the real world, by putting in a physical effort.
I am genuinely surprised when the chatbot manually recognizes previous indoor simulation rides with names like Campolongo and Giau from my Strava-history. Something I didn’t explicitly tell the chatbot, but relevant nonetheless: these are the names of mountain passes I’ll have to climb tomorrow.
And, of course, Claude upholds the questionable reputation of LLMs when it comes to language proficiency. After four training sessions in one week, it concludes that I “really jailed it” this week. Saywhat?!
Is this Big Tech’s latest Trojan horse?
So much for the pleasant surprise and practical benefits of these new AI capabilities. What is possible for cycling can also be applied for journalistic use. When newsrooms provide MCP-connections, their users can call up a financial or sports updates every day, tailored to their particular interest and knowledge level, filtered for markets and sports that are important to them. And then happily chat about their favourite’s Men’s World Cup Soccer goalkeeper.
Remember Hans, who asked if he should get involved in these kinds of experiments? Well, it seems convenient and helpful for our audiences. But it does also mean that our stories become even more ’trapped’ in the chatbot’s environment. Which subsequently increasingly captures our audience and their attention, and commercializes on all of these aspects.
Seen in this light, offering an MCP is more akin to rolling out a red carpet for Big Tech’s next Trojan horse. Besides this power-political danger, there are two other dangers that are economic and editorial by nature. That’s because by now, your stories live out there on someone else’s, not-well governed digital platform and are being scraped without consent, credit or compensation (triple C’s), as raw material for large language models.
As AI-companies start to happily connect their software and platforms with our apps and services, our content will see many more touchpoints, again mostly without the triple C’s being addressed. Unless publishers close deals with those new platforms, it’s journalists once again gain who gain no financial benefit
from this new technology.
(An other thing I learned in Perugia, is that it’s worth more than a pretty penny to most publishers if they would only know how and where parts of their content lives within these chatbot-surfaces, aka as part of generated responses to users)
Most importantly, there’s an editorial danger regarding MCP: we – or our news publisher – are being kept from (or negotiated out of) a position to manage the additional data streams and processing points ourselves. In doing so, we create new vulnerabilities to the security and privacy of our editorial data, our sources, and our stories.
On its surface, it seems convenient if Good Tape connects your transcripts to your chat account via MCP, but who says that OpenAI or Anthropic (or any other 3rd party) will treat the contents of that interview carefully and non-commercially? What if your chatbot or MCP server gets hacked? What if access to a model or platform is cut-off by executive order?
Who gets the final call?
On a technical and functional level, MCP as a protocol is pretty interesting. New opportunities and ideas created through connecting services, reveal themselves immediately at the first prompt, and it is just a natural language sentence away to build something usable and useful. Also, the fact that the industry somehow managed to arrive at a protocol at all, is a powerful signal that universal agreements aimed at cooperation are still possible in this day and age. But the technology works primarily to the advantage of the already powerful.
AI fanboys—and people with an agenda or other, selectively informed individuals—tend to draw conclusions too quickly and superficially based on their non-representative, personal experiences. They do not take the socio-economic context of every technology (it always has to ‘live’ somewhere, right?) into account in their promises-and-prediction-laden posts on LinkedIn. They view the output of language models as unequivocally valuable. Always accompanied by the obligatory disclaimer that some human still needs to check at the end of the loop to check to what extent the slop is sound. Just like the language models themselves, most of their promises eventually hold no water upon closer inspection.
But hey, I am no better myself. AI evangelists demonstrate their confirmation bias by often providing somewhat contrived examples and pointing to simplistic benefits that primarily align with their existing beliefs. I do the same thing, but in their opposite direction. If I detect some shortcoming of an AI application, I wave away actual utility or, easy as that, an entire category. Always accompanied by my predictable spiel on humanity, moral uplift, and democracy-preserving arguments.
However. Many tech bros make extraordinary claims without providing extraordinary evidence. Consider, for example, the predicted mass unemployment caused by AI, or the ever-imminent superintelligence. They advocate that using AI tools in a smart and responsible way, will make the difference between the haves and the have-nots.
Ask questions, perform a linguistic act.
Carissa Véliz, a philosopher at the University of Oxford, in her latest book ‘Prophecy’, writes that a prediction can be descriptive or prescriptive. A weather forecast does not influence the weather. The promises of Big Tech, on the other hand, are ‘veiled commands’. If we believe them and act accordingly, they create self-fulfilling prophecies.
Fortunately, language belongs to everyone, and journalists make prescriptive statements just as much. However, we use the language we employ to reinforce our own futures too infrequently. In this context, Véliz refers to the concept of the ‘language act’ (as originated by philosophers JL Austin and John Searle): an action that takes place because something is said with a certain goal in mind, such as ‘clean up your room’. Perhaps that is what MCP servers are for: They help us to perform technological actions through language.
Hans, to get back to your question: first ask yourself whether and how new AI software serves editorial purposes. If you start with that, you won’t need to try out most AI programs yourself. Use your language to set people and ideas in motion, not machines.
Tomorrow in the Dolomites, when I cycle up that final mountain, my legs burning, drenched in sweat, exhausted, I can prompt whomever I want… but I really need to reach that top on my own.
You’d wish Claude could experience something like that.
Note regarding this experiment:
Against my better judgment, I developed some FOMO regarding the latest developments in AI. Precisely to avoid simple counterclaims or criticism from the comfort of my armchair, I allowed myself to be tempted to join the camp of the chatters, vibecoders, and AI-to engage agents. I did have (and still have) some moral difficulty undertaking this experiment. For quite some time now, I have used
virtually no generative AI software, no large
language models nor chatbots, due to their extensively researched and demonstrated problematic aspects. I view this experiment as an exception that -hopefully— serves some broader benefit.
–
This piece was originally commissioned by and published in Dutch at Villamedia, June 24, 2026