In a current version of The Sequence Engineering e-newsletter, “Why Did MCP Win?,” the authors level to context serialization and trade as a motive—maybe an important motive—why everybody’s speaking concerning the Mannequin Context Protocol. I used to be puzzled by this—I’ve learn a variety of technical and semitechnical posts about MCP and haven’t seen context serialization talked about. There are tutorials, lists of accessible MCP servers, and far more however nothing that mentions context serialization itself. I used to be much more puzzled after studying by the MCP specification, during which the phrases “context serialization” and “context trade” 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 by a normal 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 offers methods for purposes to inform fashions about their capabilities in order that brokers can use these capabilities to finish a job. 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 technology of purposes that use networks of fashions, sharing context opens up new prospects.
Be taught sooner. Dig deeper. See farther.
Right here’s a comparatively easy instance. You might be utilizing AI to put in writing 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 adjustments—not an enormous deal, and a few AI instruments like Aider can already try this. However you additionally need to ship a message to your supervisor and staff members describing the challenge’s present state. Your AI-enhanced IDE would possibly be capable to generate an electronic mail. However Gmail has its personal integrations with Gemini for writing electronic mail, and also you’d want to make use of that. So your IDE can bundle the whole lot related about your context and ship it to Gemini, with directions to determine what’s essential, 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 we have now 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 verify that the outcome 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 advanced. Think about an AI utility that helps farmers plan what they may plant. That utility would possibly 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 gas costs
- A climate service
- An agronomy mannequin that predicts what crops will develop nicely 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 job of predicting climate, and the monetary business is utilizing AI to do financial modeling. One might think about doing this all on an enormous “know the whole lot” LLM (perhaps 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 variety of essential knowledge that isn’t public. So ought to fashions that forecast seed costs, fertilizer costs, and gas costs. All of those fashions are most likely subscription-based companies. It’s seemingly that a big farming enterprise or cooperative would develop proprietary in-house fashions.
The farmer’s AI wants to assemble info from these specialised fashions by sending context to them: what the farmer needs 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 supply 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 outcome; a dialog must occur between the specialist AIs as a result of every reply will affect the others. It could be potential to foretell the climate with out figuring out about economics, however you may’t do agricultural economics when you don’t perceive the climate. That is the place MCP’s worth actually lies. Constructing an utility that asks fashions questions? That’s undoubtedly helpful, however any highschool pupil can construct an app that sends a immediate to ChatGPT and screen-scrapes the outcomes. Anthropic’s laptop use API goes a step additional by automating the click 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 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 argues, intelligence is collective and social. MCP provides us the instruments to construct synthetic social intelligence.
The business 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 adequate, however we had been lacking an essential piece of the puzzle: the flexibility to ship context from one mannequin to a different. MCP offers a number of the lacking items. Google’s new A2A protocol offers extra of them. That’s what context serialization is all about, and that’s what it allows: networks of collaborating AIs, every performing as a specialist. Now, the one query is: What’s going to we construct?