petal-components-mcp
OfficialThis server lets AI assistants discover and inspect petal_components so they can generate correct HEEx markup.
list_components: list every available petal_components component with a one-line summary.get_component: fetch a component's full schema (attrs, slots, defaults, allowed values, docs) and a HEEx usage example by component name.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@petal-components-mcp Show me the schema for the Button component"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
petal-components-mcp
An MCP server that exposes petal_components — the Shadcn-style component library for Phoenix LiveView — to AI coding assistants (Claude Code, Cursor, Windsurf, etc).
Without this, AI agents writing HEEx invent raw Tailwind soup and never reach for pc_* components. With it, the AI gets the full schema for every component on demand — attrs, slots, defaults, allowed values, usage examples — and writes idiomatic petal_components markup by default.
Install (Claude Code)
claude mcp add petal --transport http https://mcp.petal.buildThen in any Phoenix project, ask the AI to build something. It'll call list_components and get_component to ground its output in real petal_components schemas.
Related MCP server: daisyui-mcp-server
Available tools
get_install_instructions- step-by-step install for a Phoenix project (dep, Tailwind v4 CSS,use PetalComponents, JS hooks), plus an optional step that syncs the petal_components usage rules intoCLAUDE.mdorAGENTS.mdvia usage_ruleslist_components- every component in the library with a one-line summaryget_component- full schema (attrs, slots, defaults, values, docs) + HEEx usage example
Coming soon: search_components (natural-language match) and generate_pattern (composed blocks like form-in-card, modal-with-form, dashboard skeletons).
How it works
The MCP server is a thin TypeScript service that bundles a JSON snapshot of every component in petal_components. The JSON is generated by a Mix task that introspects Phoenix.Component.__components__/0 on every loaded PetalComponents.* module — so the schemas are always in sync with the actual library, no manual duplication.
petal_components (Hex) petal-components-mcp (this repo)
│ │
│ mix run extract_schemas.exs │
│─────────────────────────────────────► src/schemas.json
│
│ tsc
▼
dist/server.js ◄── deployed to FlyRunning locally
# Regenerate schemas from the latest petal_components on Hex
npm run extract # cd scripts/extract && mix deps.get && mix run extract_schemas.exs
# Build and serve
npm install
npm run build
PORT=8765 npm start
# Health check
curl http://localhost:8765/healthzThe extraction is self-contained — scripts/extract/ is a tiny Mix project that pulls petal_components from Hex, introspects every Phoenix.Component.__components__/0, and writes src/schemas.json. No need for a local petal_components clone.
To use a local server with Claude Code:
claude mcp add petal-local --transport http http://localhost:8765/mcpDeploy (Fly.io)
The MCP server is hosted at mcp.petal.build on Fly.io as a standalone app.
First-time setup
# 1. Create the app (one-time, requires Fly auth)
fly apps create petal-components-mcp
# 2. Deploy
fly deploy --remote-only
# 3. Add the custom domain
fly certs add mcp.petal.buildAfter step 3, Fly prints the DNS records you need. Add a CNAME at the petal.build DNS provider:
mcp.petal.build CNAME petal-components-mcp.fly.devThen fly certs check mcp.petal.build will go green once propagation hits.
Subsequent deploys
fly deploy --remote-onlySyncing after a new petal_components release on Hex
# 1. Regenerate schemas from the latest petal_components on Hex
npm run extract
# 2. Eyeball the diff (catches surprises before they ship to AI agents worldwide)
git diff src/schemas.json | head -50
# 3. Commit and deploy
git add src/schemas.json
git commit -m "chore: sync schemas with petal_components vX.Y.Z"
git push
fly deploy --remote-onlyThe /healthz endpoint reports the bundled version, so you can confirm a deploy went out:
curl https://mcp.petal.build/healthz
# {"ok":true,"petal_components_version":"3.2.0","components":79,...}Background
This is the artifact for bet 002 — testing whether AI coding assistants become the dominant install/discovery channel for Phoenix UI tooling. See the bet for hypothesis, metrics, and kill criteria.
License
MIT.
Available Tools
2 toolsget_componentAInspect
Get the full schema for a single petal_components component — attrs, slots, defaults, allowed values, and a HEEx usage example. Call this any time you're about to write a Phoenix LiveView component reference like <.pc_button> or <.input>, to ensure the attrs and slots match the real library.
Inputs: name (required).
list_componentsAInspect
List every component available in petal_components (the Shadcn-style Phoenix LiveView component library). Use this first to see what's available before composing HEEx markup.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
Each tool has a distinct purpose: list_components provides an overview, get_component provides detailed schema for a single component. No overlap.
Both tools follow a consistent verb_noun pattern in snake_case (list_components, get_component), which is predictable and clear.
Two tools is minimal but appropriate for the server's read-only purpose of querying component schemas. A few more tools (e.g., search) could enhance, but not essential.
Covers the full lifecycle of accessing component information: listing all components and retrieving detailed schema for one. No gaps for the intended use case.
Maintenance
Related MCP Connectors
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Related MCP Servers
- AlicenseAqualityBmaintenanceA mcp server to allow LLMS gain context about shadcn ui component structure,usage and installation107,183 npm3,098MIT
- AlicenseAqualityBmaintenanceMCP server for daisyUI React components that enables AI coding assistants to search documentation, look up props, and retrieve code examples.55 npm2MIT
- AlicenseAqualityBmaintenanceMCP server that provides access to Livewire Flux components and layouts documentation, enabling AI assistants to fetch and search through documentation on demand.4398 npm9MIT
- AlicenseAqualityDmaintenanceMCP server that provides AI agents with accurate, hallucination-free access to web component APIs by reading the library's Custom Elements Manifest.7971 npm5MIT