The next article initially appeared on Block’s weblog and is being republished right here with the creator’s permission.
These days, I’ve seen extra builders on-line beginning to aspect eye MCP. There was a tweet by Darren Shepherd that summed it up effectively:
Most devs had been launched to MCP via coding brokers (Cursor, VS Code) and most devs wrestle to get worth out of MCP on this use case…so they’re rejecting MCP as a result of they’ve a CLI and scripts out there to them that are approach higher for them.
Truthful. Most builders had been launched to MCPs via some chat-with-your-code expertise, and generally it doesn’t really feel higher than simply opening your terminal and utilizing the instruments . However right here’s the factor…
MCPs weren’t constructed only for builders.
They’re not only for IDE copilots or code buddies. At Block, we use MCPs throughout every little thing, from finance to design to authorized to engineering. I gave an entire discuss on how totally different groups are utilizing goose, an AI agent. The purpose is MCP is a protocol. What you construct on prime of it could serve all types of workflows.
However I get it… Let’s discuss in regards to the dev-specific ones that are price your time.
GitHub: Extra Than Simply the CLI
In case your first thought is “Why would I take advantage of GitHub MCP when I’ve the CLI?” I hear you. GitHub’s MCP is form of bloated proper now. (They know. They’re engaged on it.)
But in addition: You’re considering too native.
You’re imagining a solo dev setup the place you’re in your terminal, utilizing GitHub CLI to do your factor. And truthfully, if all you’re doing is opening a PR or checking points, you in all probability ought to use the CLI.
However the CLI was by no means meant to coordinate throughout instruments. It’s constructed for native, linear instructions. However what in case your GitHub interactions occurred someplace else totally?
MCP shines when your work touches a number of methods like GitHub, Slack, and Jira with out you stitching it collectively.
Right here’s an actual instance from our crew:
Slack thread. Actual builders in actual time.
Dev 1: I believe there’s a bug with xyz
Dev 2: Let me verify… yep, I believe you’re proper.
Dev 3: @goose is there a bug right here?
goose: Yep. It’s in these strains… [code snippet]
Dev 3: Okay @goose, open a problem with the small print. What options would you counsel?
goose: Listed here are 3 solutions: [code snippets with rationale]
Dev 1: I like Choice 1
Dev 2: me too
Dev 3: @goose, implement Choice 1
goose: Performed. Right here’s the PR.
All of that occurred in Slack. Nobody opened a browser or a terminal. Nobody context-switched. Challenge monitoring, triaging, discussing fixes, implementing code in a single thread in a five-minute span.
We’ve additionally obtained groups tagging Linear or Jira tickets and having goose absolutely implement them. One crew had goose do 15 engineering days price of labor in a single dash. The crew actually ran out of duties and needed to pull from future sprints. Twice!
So sure, GitHub CLI is nice. However MCP opens the door to workflows the place GitHub isn’t the one place the place dev work occurs. That’s a shift price listening to.
Context7: Docs That Don’t Suck
Right here’s one other ache level builders hit: documentation.
You’re working with a brand new library. Or integrating an API. Or wrestling with an open supply device.
The Context7 MCP pulls up-to-date docs, code examples, and guides proper into your AI agent’s mind. You simply ask and get solutions to questions like:
- How do I create a fee with the Sq. SDK?
- What’s the auth circulation for Firebase?
- Is that this library tree-shakable?
It doesn’t depend on stale LLM coaching information from two years in the past. It scrapes the supply of reality proper now. Giving it up to date…say it with me…CONTEXT.
Developer “circulation” is actual, and each interruption steals treasured focus time. This MCP helps you determine new libraries, troubleshoot integrations, and get unstuck with out leaving your IDE.
Repomix: Know the Complete Codebase With out Studying It
Think about you be part of a brand new mission or wish to contribute to an open supply one, but it surely’s an enormous repo with a lot of complexity.
As a substitute of poking round for hours attempting to attract an architectural diagram in your head, you simply inform your agent: “goose, pack this mission up.”
It runs Repomix, which compresses the whole codebase into an AI-optimized file. From there, your convo would possibly go like this:
- The place’s the auth logic?
- Present me how API calls work.
- What makes use of UserContext?
- What’s the structure?
- What’s nonetheless a TODO?
You get direct solutions with context, code snippets, summaries, and solutions. It’s like onboarding with a senior dev who already is aware of every little thing. Positive, you can grep round and piece issues collectively. However Repomix offers you the entire image—construction, metrics, patterns—compressed and queryable.
And it even works with distant public GitHub repos, so that you don’t must clone something to start out exploring.
That is in all probability my favourite dev MCP. It’s an enormous time saver for brand spanking new tasks, code opinions, and refactoring.
Chrome DevTools MCP: Internet Testing Whereas You Code
The Chrome DevTools MCP is a must have for frontend devs. You’re constructing a brand new kind/widget/web page/no matter. As a substitute of opening your browser, typing stuff in, and clicking round, you simply inform your agent: “Check my login kind on localhost:3000. Strive legitimate and invalid logins. Let me know what occurs.”
Chrome opens, check runs, screenshots captured, community visitors logged, console errors famous. All completed by the agent.
That is gold for frontend devs who wish to truly check their work earlier than throwing it over the fence.
May you script all this with CLIs and APIs? Positive, if you wish to spend your weekend writing glue code. However why would you wish to try this when MCP offers you that energy proper out of the field… in any MCP shopper?!
So no, MCPs are usually not overhyped. They’re the way you plug AI into every little thing you employ: Slack, GitHub, Jira, Chrome, docs, codebases—and make that stuff work collectively in new methods.
Lately, Anthropic referred to as out the actual concern: Most dev setups load instruments naively, bloat the context, and confuse the mannequin. It’s not the protocol that’s damaged. It’s that most individuals (and brokers) haven’t discovered the way to use it effectively but. Fortuitously, goose has—it manages MCPs by default, enabling and disabling as you want them.
However I digress.
Step outdoors the IDE, and that’s if you actually begin to see the magic.
PS Completely happy first birthday, MCP! 🎉
