In a current version of The Sequence Engineering e-newsletter, “Why Did MCP Win?,” the authors level to context serialization and trade 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 whole lot of technical and semitechnical posts about MCP and haven’t seen context serialization talked about. There are tutorials, lists of obtainable MCP servers, and far more however nothing that mentions context serialization itself. I used to be much more puzzled after studying by means of the MCP specification, during which the phrases “context serialization” and “context trade” don’t seem.
What’s occurring? 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 by means of an ordinary 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 job. Nevertheless 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 most recent era of purposes that use networks of fashions, sharing context opens up new prospects.
Right here’s a comparatively easy instance. Chances are you’ll be utilizing AI to write down a program. You add a brand new characteristic, check it, and it really works. What occurs subsequent? From inside your IDE, you possibly can name conventional purposes like Git to commit the adjustments—not a giant deal, and a few AI instruments like Aider can already try this. However you additionally need to ship a message to your supervisor and crew members describing the undertaking’s present state. Your AI-enhanced IDE may be capable to generate an e mail. However Gmail has its personal integrations with Gemini for writing e mail, and also you’d desire to make use of that. So your IDE can package deal every part related about your context and ship it to Gemini, with directions to resolve what’s necessary, 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 conventional utility, now now we have two AIs collaborating to finish a job. There may even be a dialog between the AIs about what to say within the message. (And you’ll want to affirm that the outcome meets your expectations—vibe emailing to a boss looks like an antipattern.)
Now we are able to begin speaking about networks of AIs working collectively. Right here’s an instance that’s solely considerably extra advanced. Think about an AI utility that helps farmers plan what they may plant. That utility may need to use:
- An economics service to forecast crop costs
- A service to forecast seed costs
- A service to forecast fertilizer costs
- A service to forecast gasoline costs
- A climate service
- An agronomy mannequin that predicts what crops will develop effectively on the farm’s location
The applying would most likely 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 very good job of predicting climate, and the monetary trade is utilizing AI to do financial modeling. One might think about doing this all on a large, “know every part” LLM (possibly GPT-6 or 7). However one factor we’re studying is that smaller, specialised fashions typically outperform giant generalist fashions of their areas of specialization. An AI that fashions crop costs ought to have entry to a whole lot of necessary information that isn’t public. So ought to fashions that forecast seed costs, fertilizer costs, and gasoline costs. All of those fashions are most likely subscription-based companies. It’s doubtless 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 needs to know, in fact, 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 supply of assets 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 outcome; a dialog must occur between the specialist AIs as a result of every reply will affect the others. It could be attainable to foretell the climate with out figuring out about economics, however you possibly can’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 press and screen-scraping. The true worth is in connecting fashions to one another to allow them to have conversations—so {that a} mannequin that predicts the value of corn can uncover climate forecasts for the approaching yr. We will 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 are able to’t simply think about it, we are able to begin constructing it. As Blaise Agüera y Arcas argues, intelligence 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 latest burst of agentic dialogue began simply over a yr in the past. For the previous yr we’ve had fashions that had been ok, however we had been lacking an necessary piece of the puzzle: the flexibility to ship context from one mannequin to a different. MCP supplies among 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’s going to we construct?
