mcp-primer
An MCP server that enables AI models to render GitHub's Primer React components directly within chat interfaces using a JSON component tree. It provides tools to list available components and display interactive UI elements with full GitHub theming support.
README
mcp-primer
MCP App that renders Primer React components inline in AI conversations. Built on the MCP Apps extension.

What it does
Exposes two MCP tools:
| Tool | Description |
|---|---|
render-primer |
Renders a Primer component tree from JSON inline in the conversation |
list-components |
Returns available components with usage examples |
The LLM sends a component tree as JSON, and the MCP App renders it using real @primer/react components with full GitHub theming (light + dark mode).
Example
Ask Copilot: "Show me a PR status using Primer components"
The LLM calls render-primer with:
{
"tree": {
"type": "Stack",
"props": { "direction": "horizontal", "align": "center", "gap": "normal" },
"children": [
{ "type": "StateLabel", "props": { "status": "pullOpened" }, "children": "Open" },
{ "type": "Heading", "props": { "as": "h3" }, "children": "Add dark mode support" }
]
}
}
And it renders as real Primer components in the chat.
Setup
VS Code (Insiders)
Add to your MCP settings (.vscode/mcp.json):
{
"servers": {
"primer": {
"command": "node",
"args": ["${workspaceFolder}/dist/main.js", "--stdio"]
}
}
}
Or point to the repo wherever you cloned it:
{
"servers": {
"primer": {
"command": "bash",
"args": ["-c", "cd ~/source/mcp-primer && npm run build >&2 && node dist/main.js --stdio"]
}
}
}
HTTP Transport
npm start
# Server listening on http://localhost:3001/mcp
Development
npm install
npm run dev # Watch mode (Vite + server)
Available Components
Layout: Stack, PageLayout, PageHeader
Typography: Heading, Text
Actions: Button, IconButton, ButtonGroup, LinkButton
Navigation: Breadcrumbs, Link, Pagination, UnderlineNav
Data Display: Avatar, AvatarStack, BranchName, CounterLabel, Label, StateLabel, Token, RelativeTime, Timeline
Feedback: Banner, Spinner, ProgressBar
Forms: TextInput, Textarea, Select, Checkbox, Radio, FormControl, ToggleSwitch, SegmentedControl
Overlays: ActionList, ActionMenu, Dialog
Misc: Truncate, Tooltip, Popover, TreeView, NavList
All compound components (e.g. ActionList.Item, FormControl.Label, Timeline.Badge) are also supported using dot notation.
Component Tree Format
Each node in the tree has:
{
type: string; // Primer component name
props?: object; // Component props
children?: string | node | (string | node)[]; // Text or nested components
}
Build
npm run build # Type-check + Vite bundle + compile server
Produces:
dist/mcp-app.html— single-file React app with all Primer components bundleddist/server.js— MCP serverdist/index.js— entry point (stdio + HTTP)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.