#82 · Primary category： LLM Application Frameworks
mcp-ui
UI over MCP. Create next-gen UI experiences with the protocol and SDK!
Project last updated：07/08/26
GitHub Stars
5.1K
Forks
391
Contributors
20
License
Apache-2.0
Why we included this project
For products that surface AI tools, this SDK is a practical way to turn raw MCP text responses into interactive web components. It implements the MCP Apps specification, so instead of hand-writing message handling and rendering logic, you get a standard path for delivering HTML-based UIs through the Model Context Protocol. The client and server libraries are published for Node, Python, and Ruby, which suits mixed-language stacks. Teams already running MCP servers can add buttons, forms, and live views to their tools without building a separate frontend, and LLM-driven tool calls end up feeling like native app features rather than chat-style output.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform