The Mannequin Context Protocol (MCP) is genuinely helpful. It provides individuals who develop AI instruments a standardized approach to name capabilities and entry information from exterior methods. As a substitute of constructing customized integrations for every information supply, you’ll be able to expose databases, APIs, and inner instruments by a typical protocol that any AI can perceive.
Nevertheless, I’ve been watching groups undertake MCP over the previous yr, and I’m seeing a disturbing sample. Builders are utilizing MCP to shortly join their AI assistants to each information supply they’ll discover—buyer databases, help tickets, inner APIs, doc shops—and dumping all of it into the AI’s context. And since the AI is sensible sufficient to kind by a large blob of knowledge and pick the elements which can be related, all of it simply works! Which, counterintuitively, is definitely an issue. The AI cheerfully processes large quantities of knowledge and produces cheap solutions, so no one even thinks to query the strategy.
That is information hoarding. And like bodily hoarders who can’t throw something away till their properties grow to be so cluttered they’re unliveable, information hoarding has the potential to trigger severe issues for our groups. Builders be taught they’ll fetch way more information 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 information supply takes hours as an alternative of days, many builders don’t take the time to ask what information really belongs within the context. That’s how you find yourself with methods which can be costly to run and inconceivable to debug, whereas a whole cohort of builders misses the possibility to be taught the vital information structure abilities they should construct strong 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 information. As a substitute of sustaining separate code for connectors to let AI entry information from, say, S3, OneDrive, Jira, ServiceNow, and your inner DBs and APIs, you utilize the identical easy protocol to offer the AI with all kinds of knowledge to incorporate in its context. It shortly gained traction. Corporations like Block and Apollo adopted it, and groups in every single place began utilizing it. The promise is actual; in lots of instances, the work of connecting information sources to AI brokers that used to take weeks can now take minutes. However that velocity can come at a price.
Let’s begin with an instance: a small crew engaged on an AI device that reads buyer help tickets, categorizes them by urgency, suggests responses, and routes them to the correct division. They wanted to get one thing working shortly however confronted a problem: That they had buyer information unfold throughout a number of methods. After spending a morning arguing about what information to tug, which fields had been crucial, and tips on how to construction the mixing, one developer determined to only construct it, making a single getCustomerData(customerId) MCP device that pulls every thing they’d mentioned—40 fields from three completely different methods—into one large response object. To the crew’s reduction, 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 information simply high quality, and everybody felt just like the mission was heading in the right direction.
Day two, somebody added order historical past so the assistant may 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 total dialog threads, and mixed all of them into an ever-growing information object.
The assistant saved producing reasonable-looking solutions, whilst the info it ingested saved rising in scale. Nevertheless, the mannequin now needed to wade by 1000’s of irrelevant tokens earlier than answering easy questions like “Is that this buyer eligible for a refund?” The crew ended up with a knowledge structure that buried the sign in noise. That extra load put stress on the AI to dig out that sign, resulting in severe potential long-term issues. However they didn’t notice it but, as a result of the AI saved producing reasonable-looking solutions. As they added extra information 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 information supply. What had been a very beneficial device turned a bear to take care of.
The crew had fallen into the information hoarding lure: Their early fast wins created a tradition the place individuals 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 information sources.
The Expertise That By no means Develop
There are as many opinions on information structure as there are builders, and there are often some ways to unravel anyone drawback. One factor that nearly everybody agrees on is that it takes cautious selections and plenty of expertise. Nevertheless it’s additionally the topic of plenty of 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 information.
Most of us fall into just-in-case pondering at one time or one other, particularly early in our careers—pulling all the info we’d probably want simply in case we’d like it fairly than fetching solely what we’d like after we really need it (which is an instance of the other, just-in-time pondering). Usually after we’re designing our information structure, we’re coping with quick constraints: ease of entry, dimension, indexing, efficiency, community latency, and reminiscence utilization. However after we use MCP to offer information to an AI, we are able to usually sidestep a lot of these trade-offs…briefly.
The extra we work with information, the higher we get at designing how our apps use it. The extra early-career builders are uncovered to it, the extra they be taught by 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 way of all of those experiences, we develop an instinct for what “an excessive amount of information” appears like—and tips on how to deal with all of these difficult 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 every thing in just some minutes, there’s no want for dialogue or debate about what’s really wanted. The AI appears to deal with no matter information you throw at it, so the code ships with out anybody questioning the design.
With out all of that have making, discussing, and debating information design selections, builders miss the possibility to construct vital psychological fashions about information possession, system boundaries, and the price of shifting pointless information 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 forestall builders from constructing the very abilities they should use these instruments successfully. Builders who rely solely on MCP to deal with messy information by no means be taught to acknowledge when information structure is problematic, similar to builders who rely solely on instruments like Copilot or Claude Code to generate code by no means be taught to debug what it creates.
The Hidden Prices of Information Hoarding
Groups use MCP as a result of it really works. Many groups fastidiously plan their MCP information structure, and even groups that do fall into the info hoarding lure nonetheless ship profitable merchandise. However MCP remains to be comparatively new, and the hidden prices of knowledge hoarding take time to floor.
Groups usually don’t uncover the issues with a knowledge hoarding strategy till they should scale their purposes. That bloated context that hardly registered as a price to your first hundred queries begins displaying up as an actual line merchandise in your cloud invoice if you’re dealing with thousands and thousands of requests. Each pointless discipline you’re passing to the AI provides up, and also you’re paying for all that redundant information on each single AI name.
Any developer who’s handled tightly coupled lessons is aware of that when one thing goes flawed—and it all the time does, ultimately—it’s quite a bit tougher to debug. You usually find yourself coping with shotgun surgical procedure, that actually disagreeable state of affairs the place fixing one small drawback requires adjustments that cascade throughout a number of elements of your codebase. Hoarded information creates the identical sort of technical debt in your AI methods: When the AI provides a flawed reply, monitoring down which discipline it used or why it trusted one system over one other is troublesome, usually inconceivable.
There’s additionally a safety dimension to information hoarding that groups usually miss. Every bit of knowledge you expose by an MCP device is a possible vulnerability. If an attacker finds an unprotected endpoint, they’ll pull every thing that device supplies. In the event you’re hoarding information, that’s your total buyer database as an alternative of simply the three fields really wanted for the duty. Groups that fall into the info hoarding lure discover themselves violating the precept of least privilege: Purposes ought to have entry to the info they want, however no extra. That may deliver an infinite safety threat to their complete group.
In an excessive case of knowledge hoarding infecting a whole firm, you would possibly uncover that each crew in your group is constructing their very own blob. Assist has one model of buyer information, gross sales has one other, product has a 3rd. The identical buyer appears utterly completely different relying on which AI assistant you ask. New groups come alongside, see what seems to be working, and replica the sample. Now you’ve obtained information hoarding as organizational tradition.
Every crew thought they had been being pragmatic, delivery quick, and avoiding pointless arguments about information structure. However the hoarding sample spreads by a company the identical approach technical debt spreads by a codebase. It begins small and manageable. Earlier than you recognize it, it’s in every single place.
Sensible Instruments for Avoiding the Information Hoarding Lure
It may be actually troublesome to educate a crew away from information hoarding once 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 summary discussions about information possession and system boundaries when every thing they’ve carried out to this point has labored simply high quality.
In Studying Agile, Jennifer Greene and I wrote about how groups resist change as a result of they know that what they’re doing at this time works. To the particular person making an attempt to get builders to alter, it might look like irrational resistance, but it surely’s really fairly rational to push again towards somebody from the skin telling them to throw out what works at this time for one thing unproven. However similar to builders ultimately be taught that taking time for refactoring speeds them up in the long term, groups have to be taught the identical lesson about deliberate information design of their MCP instruments.
Listed here 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 pressure you to consider particular actions and naturally restrict scope. - Discuss minimizing information 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’ll run to determine what the AI really wants.
- Break reads other than reasoning. Separate information 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 may not 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 every thing. - Dashboard the waste. The perfect argument towards information hoarding is displaying the waste. Monitor the ratio of tokens fetched versus tokens used and show them in an “data radiator” model 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 enthusiastic about fixing it.
Fast odor check for information 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 may’t inform which system owns which piece of knowledge.
- Debugging requires detective work throughout a number of information sources.
- Your crew hardly ever or by no means discusses the info 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 necessary pillar of your total software structure, issues you introduce on the MCP stage ripple all through your mission. Small errors have enormous penalties down the street.
The very simplicity of MCP encourages information hoarding. It’s a straightforward lure to fall into, even for knowledgeable builders. However what worries me most is that builders studying with these instruments proper now would possibly by no means be taught why information hoarding is an issue, and so they gained’t develop the architectural judgment that comes from having to make arduous selections about information boundaries. Our job, particularly as leaders and senior engineers, is to assist everybody keep away from the info hoarding lure.
If you deal with MCP choices with the identical care you give any core interface—preserving context lean, setting boundaries, revisiting them as you be taught—MCP stays what it must be: a easy, dependable bridge between your AI and the methods that energy it.
