MCP-UI – SDK that embeds interactive UI snippets via MCP
Hey, We've just open-sourced MCP-UI, a project that provides lean client and server SDKs to enable passing rich, interactive UI components over vanilla MCP. We believe it'll enable a future where AI interaction will be based on UI snippets for interactive experiences. MCP-UI is meant to be a playground to bootstrap the initiative. Hopefully, through experimentation, the community can find the best way to enable this new future. Under the hood, the SDK enables any MCP server to respond with an EmbeddedResource with a "ui://" URI. The client SDK allows hosts to render it using a…
What it does
In the maker’s words, at launch
Hey, We've just open-sourced MCP-UI, a project that provides lean client and server SDKs to enable passing rich, interactive UI components over vanilla MCP. We believe it'll enable a future where AI interaction will be based on UI snippets for interactive experiences. MCP-UI is meant to be a playground to bootstrap the initiative. Hopefully, through experimentation, the community can find the best way to enable this new future. Under the hood, the SDK enables any MCP server to respond with an EmbeddedResource with a "ui://" URI. The client SDK allows hosts to render it using a supported method (currently raw HTML or an external app) and handles follow-up interactions through events (e.g., further tool calls). We need better delivery methods, starting with React Server Components and Remote-DOM for better security. There are many other things to accomplish, such as scalable protocol negotiation. You can build with it today - GitHub: https://github.com/idosal/mcp-ui (see demo video) Docs: https://idosal.github.io/mcp-ui UI-enabled chat client with compliant sample server: https://scira-mcp-chat-indol.vercel.app (type "show tasks" to see it in action!) Inspector for local development: https://github.com/idosal/ui-inspector Further reading on UI in MCP: https://github.com/orgs/modelcontextprotocol/discussions/287 Thoughts, changes, and contributions are more than welcome! Can't wait to see what we can build with it.
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
