About useVyre Context
useVyre Context is an MCP server for developers and AI coding tools working with useVyre components. It provides current component props, variants, design tokens, examples, and anti-patterns to help guide code generation.
Key features
- 01Retrieve component context and examples
- 02List valid props and values
- 03Validate a prop value
- 04Suggest components for a use case
- 05Look up design tokens and anti-patterns
Use cases
- 01Check valid Button variants
- 02Validate a component prop before coding
- 03Choose a component for a UI need
- 04Review design tokens and known pitfalls
MCP support
The server exposes useVyre component context and validation tools to Claude Desktop and other MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
8Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| component | string | Yes | Component name (e.g. 'Button', 'Badge', 'Card') |
Details
From the project README@usevyre/mcp-server
MCP (Model Context Protocol) server for useVyre — gives Claude Desktop and other MCP clients real-time access to component context, valid props, and anti-patterns.
Setup — Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"usevyre": {
"command": "npx",
"args": ["-y", "@usevyre/mcp-server"]
}
}
}
Restart Claude Desktop. The useVyre tools will appear in the tools panel.
Available tools
| Tool | Description |
|---|---|
get_component_info | Full context for a component — props, variants, anti-patterns, examples |
get_valid_props | All valid prop names and values for a component |
check_valid_prop_value | Validate a specific prop value before generating code |
suggest_component | Find the right component for a use case |
get_token_info | Look up a design token by name or category |
get_full_context | Entire AI context block (all components + tokens) |
get_anti_patterns | All known hallucination patterns, optionally filtered by component |
get_version_info | Package version and context validity information |
Example prompts
"What are the valid variants for the Button component?"
→ get_valid_props({ component: "Button" })
"Is variant='error' valid on Alert?"
→ check_valid_prop_value({ component: "Alert", prop: "variant", value: "error" })
"What component should I use for a search box?"
→ suggest_component({ useCase: "search box with keyboard navigation" })
Docs
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.