The Mannequin Context Protocol (MCP) is genuinely helpful. It provides individuals who develop AI instruments a standardized approach to name features and entry knowledge from exterior programs. As a substitute of constructing customized integrations for every knowledge supply, you’ll be able to expose databases, APIs, and inner instruments by way of a typical protocol that any AI can perceive.
Nevertheless, I’ve been watching groups undertake MCP over the previous 12 months, and I’m seeing a disturbing sample. Builders are utilizing MCP to shortly join their AI assistants to each knowledge supply they will discover—buyer databases, assist tickets, inner APIs, doc shops—and dumping all of it into the AI’s context. And since the AI is sensible sufficient to type by way of a large blob of knowledge and select the elements which might be related, all of it simply works! Which, counterintuitively, is definitely an issue. The AI cheerfully processes huge quantities of knowledge and produces cheap solutions, so no person even thinks to query the method.
That is knowledge hoarding. And like bodily hoarders who can’t throw something away till their properties turn into so cluttered they’re unliveable, knowledge hoarding has the potential to trigger severe issues for our groups. Builders study they will fetch much more knowledge than the AI wants and supply it with little planning or construction, and the AI is sensible sufficient to take care of it and nonetheless give good outcomes.
When connecting a brand new knowledge supply takes hours as an alternative of days, many builders don’t take the time to ask what knowledge truly belongs within the context. That’s how you find yourself with programs which might be costly to run and inconceivable to debug, whereas a complete cohort of builders misses the possibility to study the vital knowledge structure abilities they should construct sturdy and maintainable purposes.
How Groups Study to Hoard
Anthropic launched MCP in late 2024 to offer builders a common approach to join AI assistants to their knowledge. As a substitute of sustaining separate code for connectors to let AI entry knowledge from, say, S3, OneDrive, Jira, ServiceNow, and your inner DBs and APIs, you employ the identical easy protocol to offer the AI with all types of knowledge to incorporate in its context. It shortly gained traction. Firms like Block and Apollo adopted it, and groups in all places began utilizing it. The promise is actual; in lots of instances, the work of connecting knowledge sources to AI brokers that used to take weeks can now take minutes. However that pace can come at a value.
Let’s begin with an instance: a small crew engaged on an AI device that reads buyer assist tickets, categorizes them by urgency, suggests responses, and routes them to the suitable division. They wanted to get one thing working shortly however confronted a problem: They’d buyer knowledge unfold throughout a number of programs. After spending a morning arguing about what knowledge to tug, which fields had been obligatory, and how you can construction the mixing, one developer determined to simply construct it, making a single getCustomerData(customerId) MCP device that pulls all the things they’d mentioned—40 fields from three completely different programs—into one large response object. To the crew’s aid, it labored! The AI fortunately consumed all 40 fields and began answering questions, and no extra discussions or choices had been wanted. The AI dealt with all the brand new knowledge simply wonderful, and everybody felt just like the venture was heading in the right direction.
Day two, somebody added order historical past so the assistant might clarify refunds. Quickly the device pulled Zendesk standing, CRM standing, eligibility flags that contradicted one another, three completely different title fields, 4 timestamps for “final seen,” plus whole dialog threads, and mixed all of them into an ever-growing knowledge object.
The assistant saved producing reasonable-looking solutions, whilst the information it ingested saved rising in scale. Nevertheless, the mannequin now needed to wade by way of hundreds of irrelevant tokens earlier than answering easy questions like “Is that this buyer eligible for a refund?” The crew ended up with an information structure that buried the sign in noise. That further load put stress on the AI to dig out that sign, resulting in severe potential long-term issues. However they didn’t understand it but, as a result of the AI saved producing reasonable-looking solutions. As they added extra knowledge sources over the next weeks, the AI began taking longer to reply. Hallucinations crept in that they couldn’t observe right down to any particular knowledge supply. What had been a extremely helpful device turned a bear to take care of.
The crew had fallen into the knowledge hoarding lure: Their early fast wins created a tradition the place folks simply threw no matter they wanted into the context, and ultimately it grew right into a upkeep nightmare that solely obtained worse as they added extra knowledge sources.
The Expertise That By no means Develop
There are as many opinions on knowledge structure as there are builders, and there are normally some ways to unravel anyone downside. One factor that nearly everybody agrees on is that it takes cautious decisions and plenty of expertise. But it surely’s additionally the topic of numerous debate, particularly inside groups, exactly as a result of there are such a lot of methods to design how your software shops, transmits, encodes, and makes use of knowledge.
Most of us fall into just-in-case pondering at one time or one other, particularly early in our careers—pulling all the information we would probably want simply in case we’d like it slightly than fetching solely what we’d like once we really want it (which is an instance of the other, just-in-time pondering). Usually once we’re designing our knowledge structure, we’re coping with speedy constraints: ease of entry, dimension, indexing, efficiency, community latency, and reminiscence utilization. However once we use MCP to offer knowledge to an AI, we are able to usually sidestep a lot of these trade-offs…quickly.
The extra we work with knowledge, the higher we get at designing how our apps use it. The extra early-career builders are uncovered to it, the extra they study by way of expertise why, for instance, System A ought to personal buyer standing whereas System B owns cost historical past. Wholesome debate is a vital a part of this studying course of. By means of all of those experiences, we develop an instinct for what “an excessive amount of knowledge” seems to be like—and how you can deal with all of these tough however vital trade-offs that create friction all through our tasks.
MCP can take away the friction that comes from these trade-offs by letting us keep away from having to make these choices in any respect. If a developer can wire up all the things in only a few minutes, there’s no want for dialogue or debate about what’s truly wanted. The AI appears to deal with no matter knowledge you throw at it, so the code ships with out anybody questioning the design.
With out all of that have making, discussing, and debating knowledge design decisions, builders miss the possibility to construct vital psychological fashions about knowledge possession, system boundaries, and the price of transferring pointless knowledge round. They spend their early life connecting as an alternative of architecting. That is one other instance of what I name the cognitive shortcut paradox—AI instruments that make growth simpler can stop builders from constructing the very abilities they should use these instruments successfully. Builders who rely solely on MCP to deal with messy knowledge by no means study to acknowledge when knowledge structure is problematic, identical to builders who rely solely on instruments like Copilot or Claude Code to generate code by no means study to debug what it creates.
The Hidden Prices of Information Hoarding
Groups use MCP as a result of it really works. Many groups rigorously plan their MCP knowledge structure, and even groups that do fall into the information hoarding lure nonetheless ship profitable merchandise. However MCP continues to be comparatively new, and the hidden prices of knowledge hoarding take time to floor.
Groups usually don’t uncover the issues with an information hoarding method till they should scale their purposes. That bloated context that hardly registered as a value on your first hundred queries begins exhibiting up as an actual line merchandise in your cloud invoice if you’re dealing with tens of millions of requests. Each pointless area you’re passing to the AI provides up, and also you’re paying for all that redundant knowledge on each single AI name.
Any developer who’s handled tightly coupled lessons is aware of that when one thing goes incorrect—and it all the time does, ultimately—it’s loads more durable to debug. You usually find yourself coping with shotgun surgical procedure, that actually disagreeable scenario the place fixing one small downside requires adjustments that cascade throughout a number of elements of your codebase. Hoarded knowledge creates the identical type of technical debt in your AI programs: When the AI provides a incorrect reply, monitoring down which area it used or why it trusted one system over one other is tough, usually inconceivable.
There’s additionally a safety dimension to knowledge hoarding that groups usually miss. Every bit of knowledge you expose by way of an MCP device is a possible vulnerability. If an attacker finds an unprotected endpoint, they will pull all the things that device offers. For those who’re hoarding knowledge, that’s your whole buyer database as an alternative of simply the three fields truly wanted for the duty. Groups that fall into the information hoarding lure discover themselves violating the precept of least privilege: Functions ought to have entry to the information they want, however no extra. That may carry an infinite safety danger to their entire group.
In an excessive case of knowledge hoarding infecting a complete firm, you would possibly uncover that each crew in your group is constructing their very own blob. Assist has one model of buyer knowledge, gross sales has one other, product has a 3rd. The identical buyer seems to be utterly completely different relying on which AI assistant you ask. New groups come alongside, see what seems to be working, and duplicate the sample. Now you’ve obtained knowledge hoarding as organizational tradition.
Every crew thought they had been being pragmatic, transport quick, and avoiding pointless arguments about knowledge structure. However the hoarding sample spreads by way of a company the identical means technical debt spreads by way of a codebase. It begins small and manageable. Earlier than you understand it, it’s in all places.
Sensible Instruments for Avoiding the Information Hoarding Entice
It may be actually tough to teach a crew away from knowledge hoarding after they’ve by no means skilled the issues it causes. Builders are very sensible—they need to see proof of issues and aren’t going to take a seat by way of summary discussions about knowledge possession and system boundaries when all the things they’ve finished to date has labored simply wonderful.
In Studying Agile, Jennifer Greene and I wrote about how groups resist change as a result of they know that what they’re doing in the present day works. To the particular person making an attempt to get builders to vary, it could appear to be irrational resistance, nevertheless it’s truly fairly rational to push again towards somebody from the surface telling them to throw out what works in the present day for one thing unproven. However identical to builders ultimately study that taking time for refactoring speeds them up in the long term, groups have to study the identical lesson about deliberate knowledge design of their MCP instruments.
Listed below are some practices that may make these discussions simpler, by beginning with constraints that even skeptical builders can see the worth in:
- Construct instruments round verbs, not nouns. Create
checkEligibility()orgetRecentTickets()as an alternative ofgetCustomer(). Verbs power you to consider particular actions and naturally restrict scope. - Discuss minimizing knowledge wants. Earlier than anybody creates an MCP device, have a dialogue about what the smallest piece of knowledge they should present for the AI to do its job is and what experiments they will run to determine what the AI actually wants.
- Break reads other than reasoning. Separate knowledge fetching from decision-making if you design your MCP instruments. A easy
findCustomerId()device that returns simply an ID makes use of minimal tokens—and won’t even should be an MCP device in any respect, if a easy API name will do. ThengetCustomerDetailsForRefund(id)pulls solely the precise fields wanted for that call. This sample retains context centered and makes it apparent when somebody’s making an attempt to fetch all the things. - Dashboard the waste. The very best argument towards knowledge hoarding is exhibiting the waste. Observe the ratio of tokens fetched versus tokens used and show them in an “data radiator” type dashboard that everybody can see. When a device pulls 5,000 tokens however the AI solely references 200 in its reply, everybody can see the issue. As soon as builders see they’re paying for tokens they by no means use, they get very inquisitive about fixing it.
Fast odor take a look at for knowledge hoarding
- Software names are nouns
(getCustomer())as an alternative of verbs(checkEligibility()). - No person’s ever requested, “Do we actually want all these fields?”
- You possibly can’t inform which system owns which piece of knowledge.
- Debugging requires detective work throughout a number of knowledge sources.
- Your crew hardly ever or by no means discusses the information design of MCP instruments earlier than constructing them.
Wanting Ahead
MCP is a straightforward however highly effective device with huge potential for groups. However as a result of it may be a critically essential pillar of your whole software structure, issues you introduce on the MCP degree ripple all through your venture. Small errors have big penalties down the street.
The very simplicity of MCP encourages knowledge hoarding. It’s a simple lure to fall into, even for skilled builders. However what worries me most is that builders studying with these instruments proper now would possibly by no means study why knowledge hoarding is an issue, and so they gained’t develop the architectural judgment that comes from having to make arduous decisions about knowledge boundaries. Our job, particularly as leaders and senior engineers, is to assist everybody keep away from the information hoarding lure.
While you deal with MCP choices with the identical care you give any core interface—retaining context lean, setting boundaries, revisiting them as you study—MCP stays what it ought to be: a easy, dependable bridge between your AI and the programs that energy it.