Material 3 MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Log level: DEBUG, INFO, WARN, ERROR | INFO |
| GITHUB_TOKEN | No | GitHub personal access token for higher API rate limits (5,000/hour vs 60/hour) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_material_componentsB | List available Material 3 components with filtering by category, complexity, and framework |
| get_component_codeB | Retrieve real source code of specific Material 3 component with variants and examples |
| get_design_tokensB | Export Material 3 design tokens in multiple formats (CSS, SCSS, JSON, JavaScript) |
| search_material_iconsB | Search Material Symbols icon library with filters and get usage code for different frameworks |
| get_accessibility_guidelinesB | Get WCAG 2.1 accessibility guidelines specific to a Material 3 component |
| manage_cache_healthB | Check cache status, verify upstream changes, and invalidate stale data |
| generate_theme_from_colorB | Generate complete Material 3 color palette from a single base color |
| suggest_components_for_use_caseA | Get AI-powered component suggestions based on use case description |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a distinct aspect of Material 3: component discovery, code retrieval, design tokens, icon search, accessibility, theme generation, cache management, and component suggestions. Even the seemingly overlapping list and suggest tools are clearly separated by purpose—catalog filtering vs. use-case-based recommendations.
All tool names follow a consistent verb_noun pattern using snake_case (list_, get_, search_, generate_, manage_, suggest_). Verbs are descriptive and uniform, making the API predictable and easy to navigate.
With 8 tools, the server is well-scoped for a Material 3 design resource. Each tool covers a fundamental need without redundancy, and the count falls comfortably within the ideal 3-15 range.
The tool surface comprehensively covers Material 3 design workflows: exploring components, retrieving code and tokens, finding icons, checking accessibility, generating themes, and even providing AI-driven suggestions. The cache management tool is a sensible operational addition, and no obvious core capability is missing.