Thread

Figma restricts MCP access to whitelisted clients, excluding Pi

187 points · 106 comments · thdr

miguel-muniz · 1790869419 · focus · HN ↗
For context: Figma has two MCPs. The local "dev" MCP that works through the Desktop app, and the remote MCP that requires a connection to Figma. Companies need to be whitelisted to use the remote MCP, which is the only one that allows agents edit access to Figma documents.
I only found out about Figma's limitation when I was trying to add the remote MCP server to GitHub Copilot Desktop and kept running into errors. Turns out they whitelisted GitHub Copilot CLI but not the Desktop app and had put a pause on enabling any more vendors. Eventually someone (not sure which side) got it working.
Kind of strange to limit edit access only to the Remote MCP when their competitors like Pen[1] and Paper[2] allow any local agent to edit.
[1] <a href="https://www.pen.dev/" rel="nofollow">https://www.pen.dev/
[2] <a href="https://paper.design/" rel="nofollow">https://paper.design/
1. cellularmitosis · 1790870998 · focus · HN ↗
  I found figma’s remote MCP to be a poor fit for iOS development (it sets tokens on fire and gives Claude the details as React+Tailwind) and got much better results by having Claude build a set of “lens” tools around their REST API (“give me all of the fonts”, “give me the layout dimensions”, “give me the colors”, etc).
  The key to making it token efficient was allowing Claude to invent its own plaintext markup format for the lens output.
  1. btown · 1790872174 · focus · HN ↗
    Is this the API surface you're referring to?
    <a href="https://developers.figma.com/docs/rest-api/file-endpoints/#get-file-nodes-endpoint" rel="nofollow">https://developers.figma.com/docs/rest-api/file-endpoints/#g...
    <a href="https://developers.figma.com/docs/rest-api/file-node-types/" rel="nofollow">https://developers.figma.com/docs/rest-api/file-node-types/
    Seems read-only, which means we're stuck with the MCP for updating Figma files... unless you've found a workaround there too?
    joombaga · 1790893882 · focus · HN ↗
    You can use their plugin API.
    <a href="https://developers.figma.com/docs/plugins/" rel="nofollow">https://developers.figma.com/docs/plugins/
    This is what I use. Load a little shim plugin and control it with whatever you want. I made the plugin poll an http server that listens for commands.
2. miguel-muniz · 1790872749 · focus · HN ↗
  To speak more broadly, Figma is in a really tough spot right now. I see more and more designers in my circle saying they are skipping design tools entirely to prototype in code or ship directly in their product's code base. Honestly I find myself doing the same.
  Figma's main value used to be in providing designers a canvas to iterate and explore ideas since the majority of designers did not code, but AI has completely changed that.
  I fear Figma's reluctance to integrate with all the popular AI tools might actually accelerate their decline. AI provides so much value, that I would rather base my software purchasing decisions around what is compatible with my AI of choice rather than pick an AI that is compatible with Figma.
  1. oh_no · 1790874237 · focus · HN ↗
    yeah it's 100% the wrong move for them to make, I think there is probably a lot of value in AI driving Figma, and if I can't do that, Figma will fall out of the ecosystem.
    miguel-muniz · 1790875401 · focus · HN ↗
    They have their own agent built into Figma, which of course uses credits which you must pay Figma for.
  2. locallost · 1790874447 · focus · HN ↗
    I think it's really interesting how these areas are merging, and I'm not sure who goes. Designers or "coders". Probably both depending on the context. The expectations though from every field seems to be that they'll be the last man standing. My best guess is, management has the worst cards.
    I am 100% in agreement that companies that try to shut down access to agents will be replaced. It's just the future for a lot of work and workflows. In a way it's an opportunity for someone.
    TeMPOraL · 1790875249 · focus · HN ↗
    > I think it's really interesting how these areas are merging, and I'm not sure who goes. Designers or "coders".
    Neither of them, not yet. What will go away is the products currently used by these groups.
    It's happening in software development, too. In the past 3 months, I used an IDE for maybe few hours total. 99% of my technical work is now easier and better done through agentic chat interface.
    miguel-muniz · 1790876438 · focus · HN ↗
    I struggled with this myself, the reality is that AI can automate the work of everyone in the traditional product team trio (pm, design, dev).
    The way I have made peace with it in my mind is at the end of the day, I am the expert in UI/UX. There are many product teams I've joined that have operated without a designer and you can tell (bless their souls). Component libraries, templates, articles, video courses, and etc. have all existed throughout this time so it's not like they've been operating completely blind to design and UX. I don't think AI would be different. Sure it may raise the floor a little, but in the end someone needs to evaluate the output and hold responsibility for the UI/UX.
    It was an uncomfortable idea to come to terms with though, I like many other designers spent a decade getting good at Figma. Figma and design almost felt intertwined for a moment, but designers have a long history of having their craft disrupted by new technology. Decades ago designers were cutting and pasting paper, then moved to digital publishing; and in product design we've gone through software such as Photoshop, Fireworks, Sketch, and Figma, just to name a few. Design has survived all this and will continue to survive in the future.
    I think the same applies to the other disciplines. Sure I could have AI spin up a backend, but I don't really have the expertise to understand whether what it is doing is good or full of security vulnerabilities.
    I don't know in the future if we will create a new path for product builders, individuals who are knowledgeable in all aspects of product management, software engineering, and product design. I also don't know if teams will have as much need for individuals with the efficiency gains from AI.
  3. varispeed · 1790876334 · focus · HN ↗
    The poor value proposition of Figma is that nobody even bothers to vibe code a competitor. It's useless.
    timcobb · 1790882975 · focus · HN ↗
    You just described Claude Design?
  4. dataviz1000 · 1790877444 · focus · HN ↗
    Everyone is in a really tough spot.
    The AI companies focused most their effort on writing software and continue to do so. Software, SaaS, and software engineers are the first to be disrupted.
    > but AI has completely changed that.
    Exactly. However, it is because AI is focused on solving writing software first which is the step to solving everything else.
    bmitc · 1790911948 · focus · HN ↗
    From what I can see, it's everyone else who is in trouble. Software engineers have years of skills of corralling complexity, navigating requirements, etc., and all of these things matter more and more in the age of LLM tooling. It seems to me that software engineers will be taking others' roles, because if you know how to wrangle LLMs, which is something software engineers do know how to do, then you can all of the sudden take over other domains.
    rpdillon · 1790940107 · focus · HN ↗
    This is closer to the reality I'm seeing. Software engineers are well positioned to understand and deploy LLMs to solve problems, even in adjacent domains. One of the engineers I work with gave a short presentation yesterday. It was quite simple. He'd just taken a series of screenshots from our product and put it into a Claude desktop session with some pretty significant prompt explaining how the screenshots related to a particular user flow and what the desired changes we were thinking about making were.
    Took about 45 minutes and produced a working mock that we could then play with and see if the UX felt right. It was surprisingly high fidelity, and while the code was entirely throw away, it helped a room full of people make decisions about how we wanted the tool to feel within the first couple of hours of thinking about the project. Designers bring a wealth of UX thinking to that discussion, but the process of creating the mock was done entirely by engineering.
    bmitc · 1790959606 · focus · HN ↗
    I think UX designers are also well-positioned, especially those that are more technical and can use LLMs.
    Basically anyone who understands systems will be fine and more and more important, even.
  5. sergiotapia · 1790883534 · focus · HN ↗
    I've had good success in my org with Paper. Non-technical people can just jam and explore ideas without worrying about Figma or whatever tools UI/UX tools. Vibes all the way down.
    evanjrowley · 1790883718 · focus · HN ↗
    Can you link us to Paper? I doubt I will find it by searching online for "Paper design tool"
    sergiotapia · 1790883834 · focus · HN ↗
    <a href="https://paper.design/" rel="nofollow">https://paper.design/
  6. jeffybefffy519 · 1790887203 · focus · HN ↗
    I always thought it was weird that Figma didnt close the gap of taking a design and implementing it in code, that seems like what AI could enable too...
    14u2c · 1790888155 · focus · HN ↗
    They tried. Figma Make was at least useful for the free tokens.
    miguel-muniz · 1790889095 · focus · HN ↗
    Figma exists as an abstraction of code, which has always made it kind of difficult for them to implement code. For example, they have css snippets in dev mode when you have a frame selected, but those aren't really that useful since it doesn't know anything about your existing code base or frameworks.
    Code connect was supposed to bridge this gap, allowing users to define how Figma components should generate relevant code snippets, but it only worked with React and they had some janky string based templating language for everything else. And of course, it meant someone would have to go through the effort of creating mappings for every component in your system. It's like writing a component twice, the same pitfall we were trying to avoid in the first place.
    Now people will just ask their AI to pull the frames from Figma through the remote MCP and have the AI implement it that way. But to that end, why not just have designers make a branch in the codebase and have them implement the UI? This is the question many of us have been asking ourselves lately.
    They continue to iterate though. They've introduced Code Layers so real codebases can render on the canvas, but in infamous Figma fashion it only works with a limited set of React codebases. Figma Make (their Lovable, Bolt.new, Claude Design like product) can also pull in existing codebases, but again it is very limited in the types of code bases it can work on.
    These limitations are all so exhuasting. It's just so much easier to use Claude Code or Codex to do what I need. At this point Figma is more of a secondary tool for when I need to document a prototype or want a canvas for exploration purposes.
    jeffybefffy519 · 1790892424 · focus · HN ↗
    The smartest thing they could have done is a platform play which is to try make their own React that was Figma native. A hard thing to do, but certainly doable if you consider where React is now...
3. guluarte · 1790874631 · focus · HN ↗
  last time i used figma you also need to pay a dev seat PER team to use the MCP
  1. miguel-muniz · 1790877357 · focus · HN ↗
    I wasn't aware of this and went to look it up to see if it's true. Then I read that the MCP is only free for a limited time and in the future they're going to start charging based on usage [1]. That's crazy
    [1] <a href="https://help.figma.com/hc/en-us/articles/32132100833559-Guide-to-the-Figma-MCP-server" rel="nofollow">https://help.figma.com/hc/en-us/articles/32132100833559-Guid...
4. TeMPOraL · 1790875110 · focus · HN ↗
  They're realizing what most product companies aren't yet (at least not openly): AI subsumes products.
  Most companies seem to still be in denial about it, and hope that if they add some more AI into their product, or do it just right, it will make sense. But it won't. AI is destined to sit on the outside, and products to be reduced into a bag of tools for AI to call.
  Taking away write access from AI tools outside their contractual control is an expected knee-jerk reaction, but it'll probably just hasten the product's slide into irrelevancy by ceding ground to competition (that will ultimately share the same fate, too, but is still in denial about it).
  1. amoorthy · 1790876691 · focus · HN ↗
    This is the crux of the issue. I think for infrequent use cases (question/answer) an MCP with tool-calls to some product makes sense.
    But for frequent use cases - something you do daily or weekly perhaps - then a native interface still has merit. i.e. I don't think AI subsumes the product in this case.
    TeMPOraL · 1790877206 · focus · HN ↗
    But it does. Even for daily use, you probably need only a fraction of the interface - but even if you need it all, the tool is usually only part of your work.
    You need other programs to do other parts of the same work - design in Figma, code in VS Code, collaboration in Google/Microsoft office suite, shitposting (er, well-being and psychological hygiene at work) in Slack, etc. AI sitting on the outside is able to operate all of them, combining their capabilities for you, to do what you want and how you want it. AI sitting inside a single product is limited only to the surface of that product, and is limited to capabilities the vendor wants.
    amoorthy · 1790877550 · focus · HN ↗
    That's a very good point. I wonder if AI within a product sometimes is substantially better than AI outside the product for a particular task. Because AI in the product is configured thoughtfully to do a great job at that task. So if quality is a requirement then AI in the product may still have merit?
    TeMPOraL · 1790880304 · focus · HN ↗
    That variant of "AI in the product" can still be viewed as a tool call for the general AI on the outside, and my point still stands. That AI / tool can be very much a commercial offering you pay for, but that's much less business than product vendors are used to today.
    While Figma could probably survive that way for some time, most software products can't, because they don't have anything special in them.
    --
    Fundamentally, a product is our industry's "unit of billable good/service". It's composed of a number of "operations" that are more or less closely related to each other, that someone grouped together into a larger whole with a User Interface, and slapped a brand on, so it can be sold.
    From user's POV, that UI is something standing in between the user and the problem they want solved. Sometimes it's what they need, other times - not quite. From vendor's POV, UI is the mechanism of control over what users can and cannot do, and a prime sales/marketing channel, because the audience is captive.
    Now, the AI sitting on the outside, operating on the functionality under UI, and composing it with functionality of other applications, gives users a superior meta-application, solving their own problem (and AI is not restricted to chat UI - there just hasn't been that much work done yet on ad-hoc, problem/user-specific UIs).
    For users, that's a win - the AI may not be perfect mode of interaction (can get close with custom UIs), but it does not obstruct them. For vendors, that's a disaster, because it destroys coherence of a product, reducing it to a bag of tool calls, with zero branding and no control/upsell surface.
    That's what I mean by AI subsuming products, and it being a mortal threat to most of the software companies today.
    amoorthy · 1790882692 · focus · HN ↗
    Makes sense what you say. Sounds like you've thought a lot about this. If you write a post somewhere I bet others on HN and beyond would fancy a discussion as it's very much a topical issue now.
    TeMPOraL · 1790884364 · focus · HN ↗
    I am in progress of reactivating my blog right now, might as well be a first post to write. I'll submit it to HN if and when I write it.
    These thoughts, I mostly refined over time on this very forum over the past year; some of those, in reverse-chronological order: <a href="https://hn.algolia.com/?dateRange=all&page=0&prefix=true&query=ai%20subsume%20author%3ATeMPOraL&sort=byDate&type=comment" rel="nofollow">https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
    EDIT: in this very thread, you have an example of why AI on the outside beats AI on the inside: <a href="https://news.ycombinator.com/item?id=49923571">https://news.ycombinator.com/item?id=49923571.
    rixed · 1790914838 · focus · HN ↗
    Exactly my experience. Yet, I believe app will not only provide data but also some custom, short lived UI widgets in places where a more specific and consistent UX makes sense. But apps will definitively lose control over the navigation and even lose track of the user (they will identify and authorize only one : the harness; who sits behind will remain a mystery)
    I've written about this "UI to AI" pivot for my own Saas (cloudywithachanceoflatency.net). I believe it's a big win/win for every party.
    einsteinx2 · 1790977427 · focus · HN ↗
    > they will identify and authorize only one : the harness; who sits behind will remain a mystery
    This doesn’t sound right to me. To connect to the MCP server the user must authenticate. It’s not like all Claude users connect to Figma using the same account, the user connects using their Figma account. So the app still has a direct customer connection even if they lose the ability to control the UI. Unless you’re imagining some other way this would work that I’m not seeing.
    rixed · 1791001749 · focus · HN ↗
    I don't believe actual users will login. The LLM through their harness will, using an identity and password found in some shared vault. The app will still do authentication but no user management. Behind an access token there might be zero, one or several humans. Dystopian version: The allow-list for the oauth redir will become the new gatekeeper in a world without local compte, and the redir client the billed entity.
    tomjen3 · 1790881269 · focus · HN ↗
    I don't see that. I would want a special tool for something that does not display well as text, like a 3D scene.
    I imagine I also want a specialized tool for, say, reviewing 3D models before printing them. And they would definitely like addresses to be shown in a navigable map.
    But that type of interface already exist (and has been #killedbygoogle) - its Google Wave.
    TeMPOraL · 1790885066 · focus · HN ↗
    Today, LLMs can vibe you that interface on the fly.
    "I need an interface like ${this specific product} for my 3D scenes, but I also need to review each 3D model, which I normally do in ${that specialized tool}, and I'd love to have the two in one UI, well integrated, so I can ${description of your process}. Make it so."
    Put that in Antigravity/Claude Code/Codex/whatever harness backed by a decent model, and good chances are, you'll have exactly what you wanted in less than half an hour.
  2. miguel-muniz · 1790877159 · focus · HN ↗
    I imagine every CEO breaks out in night sweats thinking of the Chegg stock chart. I don't envy them, these are hard waters to navigate and many of us are still blind as to where we are going. Seems like the new moat is just the data each company holds, I guess they're holding onto it for dear life
  3. reachableceo · 1790885408 · focus · HN ↗
    Yes. This. So much this.
    All of my self hosted SAAS (redmine , gitea, discourse , vaultwaden , GLPI etc etc ) (even the cloudron pass if all runs on) is exactly that.
    It’s beautiful! Of course as a self hoster that’s quite different then SAAS vendors who need to earn a profit I guess.
  4. e3dd · 1790893771 · focus · HN ↗
    "Most companies seem to still be in denial about it, and hope that if they add some more AI into their product, or do it just right, it will make sense. But it won't. AI is destined to sit on the outside, and products to be reduced into a bag of tools for AI to call."
    Missing a lot of nuance.
    It can both be true that a newcomer figures out an experience in which the tooling sits behind the scenes and has figured out various competitive advantages that may even result in monopoly.
    Your posts carry an arrogant tint - check yourself.
5. evek · 1790881198 · focus · HN ↗
  I’ve been using a 3rd party MCP that uses a desktop plugin as a bridge, it allows for llm driven design, export, etc.
  <a href="https://github.com/southleft/figma-console-mcp/tree/main" rel="nofollow">https://github.com/southleft/figma-console-mcp/tree/main
  No affiliation, just found it useful.
  1. radley · 1790902079 · focus · HN ↗
    Yeah, this one is the standard. It's pretty robust.
6. sumeetnaik · 1791020832 · focus · HN ↗
  pen.dev is going paid from 15th Oct. We might need one open source alternative now :(

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.