mcp-ext-apps
Sample App for MCP Apps Extension (SEP-1865)
Install / Use
claude mcp add hemanth -- npx -y github:hemanth/mcp-ext-appsIf the server publishes to npm under a different name, use that package instead — check the repo README.
MCP Server
Model Context Protocol server
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Skill content
View source on GitHubMCP Ext Apps
Sample implementation of MCP Apps Extension (SEP-1865) - interactive HTML/JS UIs through MCP tools.
https://github.com/user-attachments/assets/dd4c968f-1b82-4975-8b89-374933363a99
Quick Start
npm install
npm start
Open http://localhost:8080
How It Works
Host Client MCP Server
┌────────────────────┐ ┌──────────────┐
│ tools-sidebar │ ── call tool ─> │ Tools: │
│ app-container │ <── HTML UI ─── │ - dashboard │
│ [sandboxed iframe]│ │ - clock │
└────────────────────┘ └──────────────┘
localhost:8080 localhost:3001
- Host connects to MCP server, lists tools
- User clicks a tool, host calls it via MCP
- Tool returns
text/html+mcpresource withui://URI - Host renders in sandboxed iframe with CSP
- UI communicates via JSON-RPC 2.0 over
postMessage
SEP-1865 Compliance
ui://scheme for resource URIstext/html+mcpMIME type_meta.ui/resourceUriin tool responsesui/initializehandshake protocol- JSON-RPC 2.0 message format
- Sandboxed iframe with CSP headers
Scripts
npm start # Build + start server
npm run server # MCP server (port 3001)
npm run host # Host client (port 8080)
License
MIT
Related Skills
momen-cursurrules-prompt-file
40.6kCursor rules for building custom frontends with Momen.app as headless BaaS with GraphQL API, actionflows, AI agents, and Stripe integration.
ruflo
67.5k🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
headroom
65.7kCompress 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.
CowAgent
46.4kOpen-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)
