Builders lose focus 1,200 instances a day — how MCP may change that

Software program builders spend most of their time not writing code; current business analysis discovered that precise coding accounts for as little as 16% of builders’ working hours, with the remaining consumed by operational and supportive duties. As engineering groups are pressured to “do extra with much less” and CEOs are bragging about how a lot of their codebase is written by AI, a query stays: What’s finished to optimize the remaining 84% of the duties that engineers are engaged on?

Maintain builders the place they’re the most efficient

A significant perpetrator to developer productiveness is context switching: The fixed hopping between the ever-growing array of instruments and platforms wanted to construct and ship software program. A Harvard Enterprise Evaluate research discovered that the typical digital employee flips between functions and web sites practically 1,200 instances per day. And each interruption issues. The College of California discovered that it takes about 23 minutes to regain focus after a single interruption absolutely, and generally worse, as practically 30% of interrupted duties are by no means resumed. Context switching is definitely on the heart of DORA, one of the fashionable efficiency software program growth frameworks.

In an period the place AI-driven corporations try to empower their staff to do extra with much less, past “simply” giving them entry to massive language fashions (LLMs), some traits are rising. For instance, Jarrod Ruhland, principal engineer at Brex, hypothesizes that “builders ship their highest worth when targeted inside their built-in growth surroundings (IDE)”. With that in thoughts, he determined to search out new methods to make this occur, and Anthropic’s new protocol is perhaps one of many keys.

MCP: A protocol to carry context to IDEs

Coding assistants, corresponding to LLM-powered IDEs like Cursor, Copilot and Windsurf, are on the heart of a developer renaissance. Their adoption pace is unseen. Cursor turned the fastest-growing SaaS in historical past, reaching $100 million ARR inside 12 months of launch, and 70% of Fortune 500 corporations use Microsoft Copilot.

However these coding assistants had been solely restricted to codebase context, which may assist builders write code sooner, however couldn’t assist with context switching. A brand new protocol is addressing this challenge: Mannequin Context Protocol (MCP). Launched in November 2024 by Anthropic, it’s an open customary developed to facilitate integration between AI techniques, significantly LLM-based instruments, and exterior instruments and information sources. The protocol is so fashionable that there was a 500% improve of recent MCP servers within the final 6 months, with an estimated 7 million downloads in June,

One of the impactful functions of MCP is its means to attach AI coding assistants on to the instruments builders depend on day-after-day, streamlining workflows and dramatically decreasing context switching.

Take function growth for example. Historically, it entails bouncing between a number of techniques: Studying the ticket in a mission tracker, taking a look at a dialog with a teammate for clarification, looking documentation for API particulars and, lastly, opening the IDE to begin coding. Every step lives in a special tab, requiring psychological shifts that gradual builders down.

With MCP and trendy AI assistants like Anthropic’s Claude, that total course of can occur contained in the editor.

For instance, implementing a function all inside a coding assistant turns into:

The identical precept can apply to many different engineers workflow, as an example an incident response for SREs may appear like:

Nothing new beneath the solar

We’ve seen this sample earlier than. Over the previous decade, Slack has reworked office productiveness by turning into a hub for tons of of apps, enabling staff to handle a variety of duties with out leaving the chat window. Slack’s platform diminished context switching in on a regular basis workflows. 

Riot Video games, for instance, linked round 1,000 Slack apps, and engineers noticed a 27% discount in time wanted to check and iterate code, a 22% sooner time to determine new bugs and a 24% improve in function launch charge; all had been attributed to streamlining workflows and decreasing the friction of tool-switching.

Now, an identical transformation is going on in software program growth, with AI assistants and their MCP integrations serving because the bridge to all these exterior instruments. In impact, the IDE may change into the brand new all-in-one command heart for engineers, very like Slack has been for basic information staff.

MCP is probably not enterprise prepared

MCP is a comparatively nascent customary, for instance, safety wisem MCP has no built-in authentication or permission mannequin, counting on exterior implementations which might be nonetheless evolving There’s additionally ambiguity round identification and auditing — the protocol doesn’t clearly distinguish whether or not an motion was triggered by a person or the AI itself, making accountability and entry management troublesome with out further customized options. Lori MacVittie, distinguished engineer and chief evangelist in F5 Networks’ Workplace of the CTO, says that MCP is “breaking core safety assumptions that we’ve held for a very long time.”

One other sensible limitation arises when too many MCP instruments or servers are used concurrently, for instance, inside a coding assistant. Every MCP server advertises a listing of instruments, with descriptions and parameters, that the AI mannequin wants to contemplate. Flooding the mannequin with dozens of obtainable instruments can overwhelm its context window. Efficiency degrades noticeably because the device rely grows with some IDE integrations have imposed laborious limits (round 40 instruments in Cursor IDE, or ~20 instruments for the OpenAI agent) to forestall the immediate from bloating past what the mannequin can deal with

Lastly, there isn’t a refined approach for instruments to be auto-discovered or contextually prompt past itemizing all of them, so builders usually must toggle them manually or curate which instruments are lively to maintain issues working easily. Referring to that instance of Riot Video games putting in 1,000 Slack apps, we are able to see the way it is perhaps unfit for enterprise utilization.

Much less swivel-chair, extra software program

The previous decade has taught us the worth of bringing work to the employee, from Slack channels that pipe in updates to “inbox zero” electronic mail methodologies and unified platform engineering dashboards. Now, with AI in our toolkit, we have now a chance to empower builders to be extra productive. Suppose Slack turned the hub of enterprise communication.

In that case, coding assistants are well-positioned to change into the hub of software program creation, not simply the place code is written, however the place all of the context and collaborators coalesce. By holding builders of their movement, we take away the fixed psychological gear-shifting that has plagued engineering productiveness.

For any group that depends upon software program supply, take a tough take a look at how your builders spend their day; you is perhaps stunned by what you discover.

Sylvain Kalache leads AI Labs at Rootly.