In a current version of The Sequence Engineering e-newsletter, “Why Did MCP Win?,” the authors level to context serialization and alternate as a cause—maybe a very powerful cause—why everybody’s speaking concerning the Mannequin Context Protocol. I used to be puzzled by this—I’ve learn a number of technical and semitechnical posts about MCP and haven’t seen context serialization talked about. There are tutorials, lists of obtainable MCP servers, and rather more however nothing that mentions context serialization itself. I used to be much more puzzled after studying via the MCP specificationwherein the phrases “context serialization” and “context alternate” don’t seem.
What’s happening? The authors of the Sequence Engineering piece discovered the larger image, one thing extra substantial than simply utilizing MCP to let Claude management Ableton. (Although that’s enjoyable. Suno, beware!) It’s not nearly letting language fashions drive conventional purposes via a typical API. There isn’t a separate part on context serialization as a result of all of MCP is about context serialization. That’s why it’s known as the Mannequin Context Protocol. Sure, it supplies methods for purposes to inform fashions about their capabilities in order that brokers can use these capabilities to finish a activity. However it additionally provides fashions the means to share the present context with different purposes that may make use of it. For conventional purposes like GitHub, sharing context is meaningless. For the newest era of purposes that use networks of fashions, sharing context opens up new prospects.
Be taught quicker. Dig deeper. See farther.
Right here’s a comparatively easy instance. You could be utilizing AI to jot down a program. You add a brand new characteristic, take a look at it, and it really works. What occurs subsequent? From inside your IDE, you may name conventional purposes like Git to commit the modifications—not a giant deal, and a few AI instruments like Aider can already do this. However you additionally wish to ship a message to your supervisor and crew members describing the mission’s present state. Your AI-enhanced IDE would possibly be capable of generate an electronic mail. However Gmail has its personal integrations with Gemini for writing electronic mail, and also you’d favor to make use of that. So your IDE can bundle all the things related about your context and ship it to Gemini, with directions to determine what’s vital, generate the message, and ship the message by way of Gmail after it has been created. That’s completely different: As a substitute of an AI utilizing a standard utility, now now we have two AIs collaborating to finish a activity. There may even be a dialog between the AIs about what to say within the message. (And that you must verify that the consequence meets your expectations—vibe emailing a boss looks like an antipattern.)
Now we will begin speaking about networks of AIs working collectively. Right here’s an instance that’s solely considerably extra complicated. Think about an AI utility that helps farmers plan what they’ll plant. That utility would possibly wish to use:
An economics service to forecast crop pricesA service to forecast seed pricesA service to forecast fertilizer pricesA service to forecast gasoline pricesA climate serviceAn agronomy mannequin that predicts what crops will develop properly on the farm’s location
The appliance would in all probability require a number of extra companies that I can’t think about—is there an entomology mannequin that may forecast insect infestations? (Sure, there’s.) AI can already do a great job of predicting climate, and the monetary trade is utilizing AI to do financial modeling. One might think about doing this all on an enormous “know all the things” LLM (perhaps GPT-6 or 7). However one factor we’re studying is that smaller specialised fashions usually outperform massive generalist fashions of their areas of specialization. An AI that fashions crop costs ought to have entry to a number of vital knowledge that isn’t public. So ought to fashions that forecast seed costs, fertilizer costs, and gasoline costs. All of those fashions are in all probability subscription-based companies. It’s probably that a big farming enterprise or cooperative would develop proprietary in-house fashions.
The farmer’s AI wants to collect data from these specialised fashions by sending context to them: what the farmer desires to know, after all, but additionally the situation of the fields, climate patterns over the previous yr, the farm’s manufacturing over the previous few years, the farm’s technological capabilities, the provision of sources like water, and extra. Moreover, it’s not only a matter of asking every of those fashions a query, getting the solutions, and producing a consequence; a dialog must occur between the specialist AIs as a result of every reply will affect the others. It might be doable to foretell the climate with out figuring out about economics, however you may’t do agricultural economics in the event you don’t perceive the climate. That is the place MCP’s worth actually lies. Constructing an utility that asks fashions questions? That’s positively helpful, however any highschool pupil can construct an app that sends a immediate to ChatGPT and screen-scrapes the outcomes. Anthropic’s pc use API goes a step additional by automating the click and screen-scraping. The actual worth is in connecting fashions to one another to allow them to have conversations—so {that a} mannequin that predicts the worth of corn can uncover climate forecasts for the approaching yr. We are able to construct networks of AI fashions and brokers. That’s what MCP helps. We couldn’t think about this utility just some years in the past. Now we will’t simply think about it; we will begin constructing it. As Blaise Agüera y Arcas arguesintelligence is collective and social. MCP provides us the instruments to construct synthetic social intelligence.
The trade has been speaking about brokers for a while now—dozens of years, actually. The newest burst of agentic dialogue began simply over a yr in the past. For the previous yr we’ve had fashions that had been adequate, however we had been lacking an vital piece of the puzzle: the power to ship context from one mannequin to a different. MCP supplies a number of the lacking items. Google’s new A2A protocol supplies extra of them. That’s what context serialization is all about, and that’s what it allows: networks of collaborating AIs, every appearing as a specialist. Now, the one query is: What is going to we construct?
