#89 · Primary category： LLM Application Frameworks
ext-apps
Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers
Project last updated：08/12/26
GitHub Stars
2.8K
Forks
369
Contributors
45
License
Other
Why we included this project
MCP servers that only return plain text or JSON hit a wall when a user wants something interactive mid-conversation. This project extends the Model Context Protocol so a tool can serve a ui:// resource with an HTML interface, which a compliant client renders in a sandboxed iframe while keeping two-way communication with the running tool. The repository holds the formal specification, an npm SDK with React hooks, and bridge helpers for the host side, plus working examples such as a Cesium map, a Three.js scene, and sheet-music rendering. Teams running MCP servers that need richer interactions, and developers building chat clients that embed these views, will find direct value here. It is a shared standard rather than a one-off integration, so adopting it now avoids rebuilding UI plumbing for each client.
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