Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_API_KEYNoAPI key for OpenAI (gpt-4-turbo-preview). Optional if using other providers or sampling.
DEEPSEEK_API_KEYNoAPI key for DeepSeek (deepseek-chat). Optional.
OPENROUTER_API_KEYNoAPI key for OpenRouter (claude-3.5-sonnet default). Optional.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
generate_ui_specC

Generate a production-ready UI specification with multi-agent critique, WCAG AAA validation, and design system enforcement

validate_ui_specC

Validate a UI specification against design system and WCAG standards

list_design_systemsC

List available design systems

memory_statsC

Get statistics on learned/stored UI specifications

vibe_architectC

Transform natural language intent into a detailed architecture plan with ADR decisions.

vibe_codeC

Generate production code from an architecture plan.

vibe_reviewC

Multi-agent code review from three perspectives.

vibe_verifyC

Validate code/specs against WCAG, design system, and code quality.

vibe_iterateC

Continuous improvement loop: critique -> repair -> verify -> repeat.

vibe_testC

Generate comprehensive test suites from source code.

vibe_deployC

Generate deployment configs for Vercel, Docker, static hosting.

vibe_designC

Generate a landing page using curated DESIGN.md templates.

vibe_previewC

Generate a preview HTML page and Playwright test script.

vibe_docsC

Fetch documentation for a framework via Context7.

vibe_healthC

System health stats.

vibe_auditC

Full system audit: backend code quality, security, performance.

vibe_compressC

Compress JSON to TOON format — 30-60% token reduction.

vibe_benchmarkC

Run a benchmarking loop with ASCII graphs.

vibe_upgrade_designC

Upgrade a design template with senior-dev production patterns.

vibe_build_proC

Full professional build: upgrade design -> architect -> code -> verify.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
resource_default_design_system
resource_memory_stats
resource_version

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ncsound919/VibeServe'

If you have feedback or need assistance with the MCP directory API, please join our Discord server