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?
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
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?
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!
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
+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
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.
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
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
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.
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.
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.
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.
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
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!
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.
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.
> 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.
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.