Overview
Connect your AI coding assistant to the Avonni MCP server and install the Avonni Skills to build and update avonni-* components in your LWC code from plain-language prompts.
🚧 Early access. Build with AI is rolling out gradually and improving with every release. Something unclear, missing, or broken? Tell us: your feedback directly shapes what we improve next.
Describe what you want in plain language, and your AI coding assistant (Claude Code, Cursor, or GitHub Copilot) writes working avonni-* markup and code directly in your Lightning Web Components. Two tools make that possible:
🧠 Avonni MCP server
A hosted documentation service that gives the assistant accurate, always up-to-date knowledge of every avonni-* component: attributes, events, slots, styling hooks, type definitions, and utility functions.
🛠️ Avonni Skills
A step-by-step workflow that teaches the assistant how to add and configure avonni-* components in your component's HTML, JavaScript, and CSS.
In short: skills tell the agent what to do; the MCP tells it what's true. Using one without the other gives worse results. Install both.
Why you need both
AI assistants are trained on public data, so their knowledge of Avonni is incomplete and out of date. Left on their own, they invent attribute names, guess at event payloads, and produce markup that fails at runtime. The result looks plausible but doesn't work.
The two tools solve different halves of the problem:
Avonni MCP
Knowledge. Accurate documentation for every avonni-* component, plus type definitions and utility function documentation, available only for this library.
No more invented attributes or event names. The assistant looks up the real API instead of guessing.
Avonni Skills
Process. The avonni-lwc-components workflow for editing your component's HTML, JavaScript, and CSS, with resolution rules for attributes, events, types, slots, and styling hooks.
The assistant writes markup and handlers that match the real component API, in the right files.
Lightweight code, zero maintenance debt
Ask an assistant for a data table built from scratch and it will happily generate hundreds or thousands of lines of custom JavaScript. Impressive on day one. Then every one of those lines is yours to debug, re-test at each Salesforce release, and explain to the next person. Maintaining a codebase the AI wrote six months ago is nobody's favorite project.
Building on this library changes what the assistant writes:
A data table with sorting and inline editing
Hundreds to thousands of lines of custom code
About 30 lines of markup and configuration
Where the complexity lives
In your codebase
In the managed package
Who maintains it
You
Avonni, with every release
When Salesforce updates
Re-test and patch your custom code
Update the package; your markup keeps working
Evolving it later
The assistant digs through its own generated code
Change a few attributes, or ask for them
The complex machinery (rendering, sorting, drag and drop, accessibility, edge cases) lives inside the packaged avonni-* components: tested, versioned, and updated by Avonni. What lands in your component stays small enough to read in one sitting, which also makes it easy for the assistant to update reliably later.
Knowledge the other packages don't get
The lwc toolset of the MCP server exposes two capabilities reserved for this library: type definitions (ask for the exact shape of a complex attribute, like the Data Table's columns) and utility function documentation (the public helper functions that ship with the package). Your assistant uses both to generate code that compiles and runs.
In this section
Last updated
Was this helpful?