Launch HN: Manufact (YC S25) – MCP Cloud

On your website under "Thousands of dev-teams are building with mcp-use" you include a quote from your CTO (@enri). If thousands of teams are using the product, I would think you could omit this post.

I think you have a really neat product here, but these types of testimonials do you more harm than good; they sour my opinion of all other testimonials on your site. I shouldn't have to play detective.

Having to sign up to browse available MCPs stopped me dead in my tracks and made me close the tab. I won't be the only one. Perhaps consider allowing people to browse more of the site before you try to force a signup on them?

I am really impressed with your demo video, particularly the analytics, logs, and test suite features.

I'm a target customer where I have a few curious customers, but I'm not fully ready to roll it out yet across the customer base. One thing that's stopping me, what does credits mean on your pricing page? And what is the pay as you go price after you hit your limit? I would need to be able to budget this before I deploy.

The second piece - we already have a CLI, which is great for terminal based agents and what we will continue to recommend. What we really want, and I think is what you are offering, is basically an easier way to deploy a 'remote connector' to use Claude lingo so that normal users with the claude/chatgpt app can just use our MCP. Can you point me to guidelines or the right place in your open source templates to understand how I would best handle auth (or the tradeoffs in each) during the initial build phase of the MCP server?

This is cool. I was skeptical of MCP's until I made one recently. They're essentially the exact same as 1) giving your agent a CLI tool or REST API and 2) pointing it there in an AGENT.md/CLAUDE.md. Agents are great at using built-for-human CLI tools and IMO they don't need anything purpose-built for agents. The key difference, which ends up being a usability win for non-technical users, is that the MCP bundles 1 and 2 - harnesses inject the MCP tool descriptions on every session after install. Of course, that's also why you need to be careful about context bloat when using/building them

stopped using mcp and mostly using skills now. can't understand what this product does or how it could help me.

Very interesting, will keep you in mind.

Love it guys! Also working deep in the MCP space we’ve used manufact right since the start. Great product, team and new release! Congrats

we have so many problems with MCP related to auth, scopes etc... how do you guys help solve that?

Looks great, congrats Pietro & Luigi!

Looks great! Congratulations on the launch, guys!

MCP is something people think of as a "panacea" to all AI issues. I think people are beginning to realize it is just one, albeit important, part of a successful AI architecture.

congrats guys! how does the automated testing using ChatGPT/Claude clients work?

Huge congrats to the team on the official launch of Manufact!

MCP is a deadend. CLI use is the future.

we've been using manufact for months now. couldn't build mcps another way.

stopped using mcp and mostly using skills now. can't understand what this product does or how it could help me.

Huge congrats to the team on the official launch of Manufact!

I am really impressed with your demo video, particularly the analytics, logs, and test suite features.

thank you so much we have put a lot of love into our product!

pricing: we offer several credit based products that have different cost - requests, build minutes, eval runs, checklist all have different unit cost the breakdown is here https://docs.manufact.com/dashboard/billing thanks for pointing out that it should be more transparent!

auth: we published a few blogs https://manufact.com/blog/oauth-mcp https://manufact.com/blog/authentication

+ lots of auth templates you can start from https://manufact.com/templates

+1 !! Thanks for putting it so clearly, also CLIs and REST have their space in some applications, I think MCP is a way to organize them and distribute them better

Yeah MCPs are easier to distribute.

In my experience, they also work better with dumber models than CLIs (which saves money)

we have so many problems with MCP related to auth, scopes etc... how do you guys help solve that?

One issue i saw related to scopes is the offline_access one that causes frequent reauthenticate request from the client. for example codex has this bug (https://github.com/openai/codex/issues/20503). many servers solve this with some workarounds or increasing the token life. In v2 of mcp-use coming end of the month there should be a builtin way to deal with buggy clients so the server remains connected.

with our SDK we provide many adapters to popular authentication providers which basically provision oauth on your server in one line of code, here the docs https://docs.mcp-use.com/typescript/server/authentication/in...

also we ship templates for you to get started https://manufact.com/templates

You may want to have a look at Skybridge, a TypeScript framework designed to build MCP servers and MCP Apps, with a recent emphasis on making authentication easy.

Can you get into the specifics of the problems you currently experience with MCP? I'd love to learn more.

MCP is something people think of as a "panacea" to all AI issues. I think people are beginning to realize it is just one, albeit important, part of a successful AI architecture.

congrats guys! how does the automated testing using ChatGPT/Claude clients work?

thank you so much we have put a lot of love into our product!

auth: we published a few blogs https://manufact.com/blog/oauth-mcp https://manufact.com/blog/authentication

+ lots of auth templates you can start from https://manufact.com/templates

+1 !! Thanks for putting it so clearly, also CLIs and REST have their space in some applications, I think MCP is a way to organize them and distribute them better

Yeah MCPs are easier to distribute.

In my experience, they also work better with dumber models than CLIs (which saves money)

also we ship templates for you to get started https://manufact.com/templates

Can you get into the specifics of the problems you currently experience with MCP? I'd love to learn more.

First of all, people have been saying this for a long time. It’s nothing new, at least half a year, maybe closer to a year.

Secondly, it’s not even that important, it’s the tool calling itself that’s important. MCP servers are just a convenient way to interact with remote services when a command line utility for the same would be inconvenient.

MCP is a deadend. CLI use is the future.

I've been sitting in the same camp recently. We maintain both an internal MCP and CLI for our app which our devs use locally. The CLI so far feels like a much smoother experience both in terms of setup, control and performance.

But i can see how MCP being able to plug into a remote agent that doesn't have terminal access is very useful. Seems like it's a best tool for the job conversation or am I missing some other advantage?

There is definitely some debate going on on mcp/cli/api etc, but is quite obvious that mcp is being adopted as standard for integrating third party applications to the major clients => chatgpt apps, claude connectors, mistral, cursor etc.. they all connect to external apps using mcp. Of course it's possible for you to tell claude to use some cli directly but it's much easier to connect the mcp with one click

Not for every situation. CLI is great for coding agents (and I'd agree, far better in most cases than MCP). But it requires some execution runtime somewhere to actually run. So for app use cases where you don't want to build out your own tools for every integration, MCP can be a solid option.

MCP is great for docs and stuff, also saves tokens and reduces errors if you have something complicated you're abstracting over

- agents have old/inaccurate knowledge and it's nice to have up to date docs: https://awslabs.github.io/mcp/servers/aws-documentation-mcp-...

- geting agents to do apple builds and stuff is much easier with: https://github.com/getsentry/XcodeBuildMCP

- also for searching stuff like pdfs/epubs it's nice to have a place that's easy/fast for an agent to go to: https://github.com/nburns/doc-search-mcp

none of these strictly requrie mcp, but it is still a useful abstraction/shared convention

CLI certainly is better than local MCP. But nowadays, most MCPs are remote and the comparison fall short, at the notable exception of `gh` in a coding environment. But having CLI already authenticated is not guaranted either!

Could you elaborate on this thought? MCP vs CLI feels very much like a Apples/Oranges comparison, without additional context.

I am so tired of people repeating this. Usually, this results from conflating two uses of MCP: local, which can indeed be replaced by CLI (and you can argue which one is better), and remote, which is entirely different, and there is no way to replace it with a CLI (note that you are making an implicit assumption that a CLI tool can be used at all, which is not always the case).

Please don't repeat this. It's like saying that apples are dead and oranges are the future.

cached thought. running CLIs is impractical and expensive in many environments and a hell of a lot less secure than using MCP

They serve two different purposes.

Edited*

You may want to have a look at Skybridge, a TypeScript framework designed to build MCP servers and MCP Apps, with a recent emphasis on making authentication easy.

we support deploying Skybridge too https://manufact.com/blog/mcp-app-with-skybridge ! saw that you work for the company that is developing that, usually on HN to keep it honest you want to disclose that

TypeScript, for all its benefits, still feels like a toy or project language. I'd love to see a Rust, C++, or even a Go library for such purpose.

I'd love for people with experience to break me of this negativity towards TypeScript. Anybody?

First of all, people have been saying this for a long time. It’s nothing new, at least half a year, maybe closer to a year.

MCP is great for docs and stuff, also saves tokens and reduces errors if you have something complicated you're abstracting over

- agents have old/inaccurate knowledge and it's nice to have up to date docs: https://awslabs.github.io/mcp/servers/aws-documentation-mcp-...

- geting agents to do apple builds and stuff is much easier with: https://github.com/getsentry/XcodeBuildMCP

- also for searching stuff like pdfs/epubs it's nice to have a place that's easy/fast for an agent to go to: https://github.com/nburns/doc-search-mcp

none of these strictly requrie mcp, but it is still a useful abstraction/shared convention

Please don't repeat this. It's like saying that apples are dead and oranges are the future.

cached thought. running CLIs is impractical and expensive in many environments and a hell of a lot less secure than using MCP

Also, in my opinion, it's much easier to build a good MCP interface than it is to build a good CLI interface - and afaik there's support for MCP tools to return things like images from an MCP tool call directly to the calling LLM that is a bit tricker to do via CLI.

Could you elaborate on this thought? MCP vs CLI feels very much like a Apples/Oranges comparison, without additional context.

MCP makes a lot, lot more sense when you think of it as as a auth standard and not a comparison with CLIs. It obviously does more than just auth, but having standardised auth (which CLIs definitely do not) is the real 'killer' feature.

They serve two different purposes.

Edited*

> Tell me you don't understand what you're saying without telling me you don't understand what you're saying.

Please don't cross into personal attack, regardless of how wrong someone is or you feel they are.

Your comment would be fine without that last swipe, and even better if you had gone on to say what the two purposes are. Then we could learn something from it.

If you wouldn't mind reviewing https://news.ycombinator.com/newsguidelines.html and taking the intended spirit of the site more to heart, we'd be grateful.

TypeScript, for all its benefits, still feels like a toy or project language. I'd love to see a Rust, C++, or even a Go library for such purpose.

I'd love for people with experience to break me of this negativity towards TypeScript. Anybody?

a few thoughts for MCP: - typescript "runs" in the browser, which is very handy to develop browser side MCP Clients - for similar reasons it is the only real option to develop UIs for MCP Apps for instance

not particularly related to MCP: as most products rely on external APIs provided by the labs (ChatGPT wrapper as we used to call them) frontend languages become more important

> Tell me you don't understand what you're saying without telling me you don't understand what you're saying.

Please don't cross into personal attack, regardless of how wrong someone is or you feel they are.

Your comment would be fine without that last swipe, and even better if you had gone on to say what the two purposes are. Then we could learn something from it.

If you wouldn't mind reviewing https://news.ycombinator.com/newsguidelines.html and taking the intended spirit of the site more to heart, we'd be grateful.

Apologies, I appreciate you posting this!

Very interesting, will keep you in mind.

Love it guys! Also working deep in the MCP space we’ve used manufact right since the start. Great product, team and new release! Congrats

Looks great, congrats Pietro & Luigi!

Looks great! Congratulations on the launch, guys!

hey thanks for the feedback, we do not really offer a "set" of pre made MCPs that we could show pre signup, unfortunately our platform requires you to deploy something to use it - we try to give an overview of all the features in our "Platform" section in the navbar on top

noted! thanks for the feedback, will be gone soon edit: gone

we've been using manufact for months now. couldn't build mcps another way.

noted! thanks for the feedback, will be gone soon edit: gone

Build and deploy MCP Apps and Servers

The mcp-use SDK is the fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents. Loved by developers.

Our open source tools are used by developers at top companies

6sense logo

Elastic logo

IBM logo

Innovacer logo

Intuit logo

NVIDIA logo

Oracle logo

Red Hat logo

Tavily logo

Verizon logo

6sense logo

Elastic logo

IBM logo

Innovacer logo

Intuit logo

NVIDIA logo

Oracle logo

Red Hat logo

Tavily logo

Verizon logo

Your fastest path to the ChatGPT Apps Store and Claude Connectors.

One codebase. Every surface where users and agents already work.

AI Chats

ChatGPTClaudeGemini EnterpriseCopilot 365

Coding agents

CodexClaude CodeCursorVS Code

Internal agents

OpenAI AgentsClaude Agent SDKMastraLangchainVercel AI SDKCopilotKit

ChatGPT Apps Store and Claude Connectors

From first commit to production.

Every step of the MCP lifecycle. No extra tools.

deploy

One push. Live in seconds.

Connect your repo once. Every push auto-deploys to Manufact Cloud. No YAML. No Dockerfile archaeology.

GitHub App

Connect once. Every push auto-deploys to Manufact Cloud.
Preview per branch

A live, unique URL for every pull request
Custom domains

Ship your app under your own domain. SSL handled.

publish

Derisk your path to the marketplaces.

Get your app in front of users in ChatGPT and Claude. Submission assets generated for you. Share an embedded chat anywhere you already have an audience.

Marketplace checklists

Know when you're ready to submit
Submission assets

Logo, copy, and screenshots generated for you
Embedded chat

Automatic sharable chat for your mcp server

mcp.acme.com/chat

monitor

Don't go blind in production.

See how people actually use your MCP app. Analytics, session replay, and observability built in — so you catch regressions before users report them.

Analytics

Traffic, tool-call volume, and latency at a glance.
Session tracking

Replay a user's conversation end-to-end.
Observability

Traces, error rates, and alerts on regressions.

Build by hand. Or with Manufact.

BeforeWithout Manufact

AfterWith Manufact

Stitch together MCP server, React UI, hosting, auth, and scaling.

npx create-mcp-use-app scaffolds the whole stack.

Test by connecting to a live LLM and hoping.

Visual Inspector. Sandbox testing. No LLM required.

Manage your own deployment pipeline and branch previews.

git push auto-deploys via the GitHub App.

Build for ChatGPT or Claude or Gemini — separately.

Build once. Deploy to ChatGPT, Claude, and Gemini.

Developers love

Thousands of dev-teams are building with mcp-use

Built in the open.

One of the most adopted open-source MCP frameworks. Open from day one.

10k+

GitHub stars. Open-source since day one.

Contribute

<60s

From git push to live MCP App or Server.

Deploy

Begin your MCP journey
in the

fastest way

Already have an MCP server on GitHub? Deploy it with one click.

Describe what you want. Watch your MCP server and widgets scaffold in front of you.

Pick one of our templates and start from a known-good scaffold.

Hacker Times