mcpField
F
fragments-mcp

fragments-mcp

Local
github.com/ConanMcNDeveloper Tools
Repository

About fragments-mcp

Design system MCP with 9 tools for component discovery, rendering, and a11y auditing

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "conanmcn-fragments": {
      "command": "npx",
      "args": [
        "-y",
        "@fragments-sdk/mcp"
      ]
    }
  }
}
Run commandnpx -y @fragments-sdk/mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@fragments-sdk/mcp0.5.7

Tools

6

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
limitnumberNoMaximum number of results to return (default: 10 for useCase mode)
formatenumNoOutput format for context mode (default: markdown)markdown | json
searchstringNoSearch term to filter by name, description, or tags
statusenumNoFilter by component statusstable | beta | deprecated | experimental
compactbooleanNoIf true, returns minimal output (just component names and categories)
useCasestringNoDescription of what you want to build — returns ranked suggestions (e.g., "form for user email input", "button to submit data")
categorystringNoFilter by category (e.g., "actions", "forms", "layout")
componentstringNoComponent name to find alternatives for (e.g., "Button")
verbosityenumNoResponse detail level: "compact" (names only), "standard" (default), "full" (everything including code)compact | standard | full
includeCodebooleanNoIf true, includes code examples for each variant
includeRelationsbooleanNoIf true, includes component relationships

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

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.