Launch HN: Manufact (YC S25) – MCP Cloud
Summary
Manufact is a cloud platform for building and deploying MCP agents, servers, and apps, offering an SDK, automated deployment, monitoring, and marketplace submission tools.
Hi HN, we are Pietro and Luigi, cofounders of Manufact (<a href="https://manufact.com">https://manufact.com</a>), a cloud for MCP apps and servers. We used to be called mcp-use, and still build open source SDKs for MCP under that name: <a href="https://github.com/mcp-use/mcp-use" rel="nofollow">https://github.com/mcp-use/mcp-use</a>. We did a Show HN about that last year: <a href="https://news.ycombinator.com/item?id=44747229">https://news.ycombinator.com/item?id=44747229</a>.<p>Today we want to tell you about our cloud product, Manufact, which is to mcp-use as Vercel is to Next.js. Manufact is an MCP vertical cloud designed for dev teams putting MCP Apps and servers in production.You can ship, iterate on, test and monitor your MCPs, and get them ready for the store submissions. All with the best developer and agent experience in mind.<p>Here is a demo video of the product: <a href="https://www.youtube.com/watch?v=R2rbr5OT9LI" rel="nofollow">https://www.youtube.com/watch?v=R2rbr5OT9LI</a>.<p>We have been working on MCP since April 2025. Our first focus was making it easy to build agents that could use any MCP server, and a lot of people started using our SDKs. Then the harness revolution kicked off: Claude Code, Claude Cowork, ChatGPT, Codex, OpenCode started shipping agent harnesses that made most standalone agent frameworks redundant. That pushed us to the other side of the connection, the servers. If agents were going to consolidate into a few harnesses, then first-class integration with the rest of a company's systems (i.e. MCP) would become the thing that mattered, so we started building up our server SDKs.<p>Then in succession:<p>1. Oct 2025. ChatGPT Apps SDK. OpenAI brings app UIs to ChatGPT, built on top of MCP and the work of mcp-ui.
2. Late 2025. The stores open. ChatGPT starts accepting app submissions, Claude grows its connector directory with selected partners.
3. Jan 2026. MCP Apps becomes official. SEP-1865 merges as the first MCP extension (io.modelcontextprotocol/ui): one UI standard any host can render.<p>Today, all the major clients fully support MCP and are opening marketplaces of reviewed MCPs that can be one click installed. All major tech companies have an MCP server, and many of those are reporting that already 15+% of their usage comes from their MCP, and we start to have a good way to distribute them just now.<p>MCP can return fully interactive UIs. So companies can (1) display data in more meaningful ways to their users (e.g. analytics, ecommerce) and (2) display their branding in some of the most used products on the planet (ChatGPT, Claude etc). Numbers: an engineer at Amplitude reported that their MCP saw a 2x increase in retention after adding UI to their MCP.<p>Clients (Claude, ChatGPT, Cursor) are starting to dynamically present MCP servers/apps to users, based on their intent. Products will be organically discovered on the chats!<p>We feel that MCP is reaching its maturity moment. Now that MCPs are starting to be easy to install and discover, there is going to be a huge incentive for users to use them and for companies to create them:<p>1 - Most work is already done from AI chats, this is not going to stop, MCP gives you a way to interact with products without manually using their dashboards.<p>2 - MCP allows you to bring the context together in one place: you can read an email, create a ticket while plugged into the source code of your product, or your knowledge base. Aggregation of products that was not possible before, will happen in the chat, orchestrated by increasingly intelligent models.<p>If AI apps (Codex, Claude Desktop) are the new browsers, as PG said in a recent tweet <a href="https://x.com/paulg/status/2069080429236191504" rel="nofollow">https://x.com/paulg/status/2069080429236191504</a>, then MCPs are the new websites.<p>But there is a catch:<p>- Submission process on the stores is still quite tricky, manual and takes up valuable time.
- Hardly anybody knows how to design a good MCP: most of them are 1:1 proxies of the API and are abandoned, since being one shotted a few months ago.
- The MCP Spec advances quickly and it is not easy to keep track of the changes, and what they mean for your server.
- Auth is still a mystery for most teams (API key in the URL ???).
- Most companies are not even aware that MCPs can return interactive UIs.
- Clients still have to consolidate behavior, some do dynamic tool discovery, some don't, some persist authentication properly some don't.<p>We built Manufact and mcp-use to solve these problems.
Our SDKs help them build good MCPs, our inspector helps them test locally, and our cloud helps them ship/publish and monitor them in production.<p>To deploy on Manufact you just need to connect a Github app, pick the repo, we'll detect the framework you are working with and get you a live MCP url as soon as possible.<p>In our platform, that live URL will be used to give you a chat where you can try/debug your MCP immediately and share it with your team. If you push an update on a new experimental branch, you'll be able to test that as well thanks to preview deployments.<p>Once your server is ready to go live, we help you make sure that it does not break. You can configure automated tests that will take your MCP server, install it in ChatGPT and Claude and test it. We do not test the model, we test the client (model + harness). This way you reliably know if your server breaks where people use it.<p>Since publishing on the store is a major distribution unlock for companies (your MCP can be dynamically discovered and one click installed across Claude
products, and ChatGPT), we collected a set of requirements that will keep your submission from being rejected. You check this locally before going through the actual review process.<p>Once your server is live, you'll want to understand how it is used. Our analytics are designed for MCP, so you'll know how many users are hitting
your MCP, how many tool calls you receive, from which client.<p>You can try out <a href="https://manufact.com">https://manufact.com</a> for free today. We have usage-based pricing and on our free account we give free credits for you to try it out. If you have an
MCP already, just connect your Github repo and deploy, if not you can build one using our skill and SDKs pretty simply (we will guide you in the onboarding).<p>We would love to hear feedback about the product in the comments, and hear thoughts from everyone about MCP. Thanks! :)
View Cached Full Text
Cached at: 07/02/26, 05:07 PM
# Manufact | Build and Deploy MCP Agents, Servers & Apps
Source: [https://manufact.com/](https://manufact.com/)
## 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\.](https://github.com/mcp-use/mcp-use)
Our open source tools are used by developers at top companies
## 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
## 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\.
BeforeWithoutManufact
AfterWithManufact
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
[Been thinking about trying your @mcpuse today when I started building a ChatGPT app, but wasn't sure if it's the right use case\. Now I assume it is 🙂  Paolo Perazzo@SiVola](https://x.com/SiVola/status/1993838266056102191)[Great addition to the generic MCP Client collection\.  Kingsley Uyi Idehen@kidehen](https://x.com/kidehen/status/1911480727616606313)[Infra isn't just plumbing\. It's distribution\. Examples: AgentMail: inboxes for agents, mcp\-use: MCP infra, DeepAware: RL for data center ops\. Whoever owns the rails agents use to talk to the outside world ends up with Twilio\-style power\.  Vedika Jain@vedikaja\_in](https://x.com/vedikaja_in/status/1959080358215082036)[mcp\-use is by far the best Python framework for building an agent MCP\. It's so easy to set up an agent connected to MCP servers through the command line, that way I can quickly iterate on my MCP servers and test\. Most people are using MCP servers in chat clients like Cursor / Claude Code, but MCP server use by agents will explode in the near future\. I think it's important to test your server in an agent environment, and mcp\-use provides that\.  Matt Wang@mcpjams](https://x.com/mcpjams/status/1955008680719683768)[MCP\-Use is the open source way to connect any LLM to any MCP server and build custom agents that have tool access, without using closed source or application clients\.  Adam Silverman@adamsilverman](https://x.com/adamsilverman/status/1916934060175462858)[that's why we love open\-source\! @NASA is building an agent with MCP using our library @mcpuse 🚀  pederzh@pederzh](https://x.com/pederzh/status/1943477519375613989)[Been thinking about trying your @mcpuse today when I started building a ChatGPT app, but wasn't sure if it's the right use case\. Now I assume it is 🙂  Paolo Perazzo@SiVola](https://x.com/SiVola/status/1993838266056102191)[Great addition to the generic MCP Client collection\.  Kingsley Uyi Idehen@kidehen](https://x.com/kidehen/status/1911480727616606313)[Infra isn't just plumbing\. It's distribution\. Examples: AgentMail: inboxes for agents, mcp\-use: MCP infra, DeepAware: RL for data center ops\. Whoever owns the rails agents use to talk to the outside world ends up with Twilio\-style power\.  Vedika Jain@vedikaja\_in](https://x.com/vedikaja_in/status/1959080358215082036)[mcp\-use is by far the best Python framework for building an agent MCP\. It's so easy to set up an agent connected to MCP servers through the command line, that way I can quickly iterate on my MCP servers and test\. Most people are using MCP servers in chat clients like Cursor / Claude Code, but MCP server use by agents will explode in the near future\. I think it's important to test your server in an agent environment, and mcp\-use provides that\.  Matt Wang@mcpjams](https://x.com/mcpjams/status/1955008680719683768)[MCP\-Use is the open source way to connect any LLM to any MCP server and build custom agents that have tool access, without using closed source or application clients\.  Adam Silverman@adamsilverman](https://x.com/adamsilverman/status/1916934060175462858)[that's why we love open\-source\! @NASA is building an agent with MCP using our library @mcpuse 🚀  pederzh@pederzh](https://x.com/pederzh/status/1943477519375613989)
[Really sharp execution, mcp\-use nails the 'Vercel for MCP' play\. Love how you've stripped deployment and aggregation down to a single endpoint with zero friction\. Crypto infra teams, onchain data providers, and AI\-powered DeFi dashboards could slot this in to speed up agent builds massively\.  Ctran\.eth@ctranbtw](https://x.com/ctranbtw/status/1955736140260032723)[🦜🤖 MCP\-Use Tools \- Just launched: An open\-source library that connects any LLM to MCP tools for custom agents, featuring seamless integration with LangChain and support for web browsing, Airbnb search, and 3D modeling capabilities\.  LangChain@LangChainAI](https://x.com/LangChainAI/status/1911449301542195582)[<60s to deploy your ChatGPT App 🤯 With mcp\-use creating your own app takes less than a minute\. 1\. npx create\-mcp\-use\-app 2\. Edit your react widgets 3\. yarn deploy\. Done\! You can now connect your mcp server to ChatGPT and start chatting\.  Enrico Toniato@thisfounder](https://x.com/thisfounder/status/1990494825037414786)[We implemented Code Mode in mcp\-use's MCPClient \. All you need to do is define which servers you want your agent to use, enable code mode, and you're done\! The client will expose two tools: \- One that allows the agent to progressively discover which servers and tools are available \- One that allows the agent to execute code in an environment where the MCP servers are available as Python modules \(SDKs\)  Pietro@pietrozullo](https://x.com/pietrozullo/status/1991537221900394857)[Really sharp execution, mcp\-use nails the 'Vercel for MCP' play\. Love how you've stripped deployment and aggregation down to a single endpoint with zero friction\. Crypto infra teams, onchain data providers, and AI\-powered DeFi dashboards could slot this in to speed up agent builds massively\.  Ctran\.eth@ctranbtw](https://x.com/ctranbtw/status/1955736140260032723)[🦜🤖 MCP\-Use Tools \- Just launched: An open\-source library that connects any LLM to MCP tools for custom agents, featuring seamless integration with LangChain and support for web browsing, Airbnb search, and 3D modeling capabilities\.  LangChain@LangChainAI](https://x.com/LangChainAI/status/1911449301542195582)[<60s to deploy your ChatGPT App 🤯 With mcp\-use creating your own app takes less than a minute\. 1\. npx create\-mcp\-use\-app 2\. Edit your react widgets 3\. yarn deploy\. Done\! You can now connect your mcp server to ChatGPT and start chatting\.  Enrico Toniato@thisfounder](https://x.com/thisfounder/status/1990494825037414786)[We implemented Code Mode in mcp\-use's MCPClient \. All you need to do is define which servers you want your agent to use, enable code mode, and you're done\! The client will expose two tools: \- One that allows the agent to progressively discover which servers and tools are available \- One that allows the agent to execute code in an environment where the MCP servers are available as Python modules \(SDKs\)  Pietro@pietrozullo](https://x.com/pietrozullo/status/1991537221900394857)
## 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](https://github.com/mcp-use/mcp-use)
<60s
From git push to live MCP App or Server\.
[Deploy](https://manufact.com/signup)
## Begin your MCP journey in the
### From a Git repository
Already have an MCP server on GitHub? Deploy it with one click\.
### Vibecode your MCP App
Describe what you want\. Watch your MCP server and widgets scaffold in front of you\.
### From a template
Pick one of our templates and start from a known\-good scaffold\.
Similar Articles
Launch HN: Minicor (YC P26) – Windows desktop automations at scale
Minicor is a Y Combinator-backed platform that deploys self-healing AI agents for scalable desktop automations, enabling integration with legacy systems lacking APIs.
Launch HN: Traceforce (YC S26) – Company-wide security monitoring for AI apps
Traceforce provides company-wide visibility and control over AI applications like ChatGPT and Claude on all devices, discovering usage and connections via MCPs, and includes an open-source MCP pentesting tool.
Launch HN: Hyper (YC P26) – Company brain to power agentic development
Hyper is a shared company brain that ingests internal data (Slack, docs, email, etc.) into a knowledge graph with a hybrid memory system of episodes and facts, enabling AI agents to have better context and perform complex tasks more effectively.
Show HN: An MCP server that turns async-work practices into tools
An MCP server that integrates async-first working practices as tools for AI assistants, allowing users to draft decision docs, convert meetings to artifacts, score status updates, and more.
Launch HN: Coasty (YC S26) – An API for computer-use agents
Coasty is a new API for building computer-use agents, offering task runs, workflows, managed machines, and lower-level prediction primitives.