Creating MCP Apps
Those are conversational experiences that extend AI assistants through tools and custom UI widgets. They're built as MCP servers invoked during conversations.
⚠️ The app is consumed by two users at once: the human and the AI Assistant LLM. They collaborate through the widget—the human interacts with it, the LLM sees its state. Internalize this before writing code: the widget is your shared surface.
SPEC.md keeps track of the app's requirements and design decisions. Keep it up to date as you work on the app.
No SPEC.md? Stop. → Read discover.md first. Nothing else until SPEC.md exists.
Setup
- Copy template → copy-template.md: when starting a new project with ready SPEC.md
- Run locally → run-locally.md: when ready to test, need dev server or ChatGPT/Claude connection
Architecture
Design or evolve UX flows and API shape → architecture.md
Implementation
- Fetch and render data → fetch-and-render-data.md: when implementing server handlers and widget data fetching
- State and context → state-and-context.md: when persisting widget UI state and updating LLM context
- Prompt LLM → prompt-llm.md: when widget needs to trigger LLM response
- UI guidelines → ui-guidelines.md: display modes, layout constraints, theme, device, and locale
- External links → open-external-links.md: when redirecting to external URLs or setting "open in app" target
- OAuth → oauth.md: when tools need user authentication to access user-specific data
- CSP → csp.md: when declaring allowed domains for fetch, assets, redirects, or iframes
Deploy
- Ship to production → deploy.md: when ready to deploy via Alpic
- Publish to ChatGPT/Claude Directories → publish.md: when ready to submit for review
Full API docs: https://docs.skybridge.tech/api-reference.md