Schema | red-design-mcp

red-design-mcp

Describes the environment variables required to run the server.

Name	Required	Description
`RED_MODEL`	No	Override the model name used by the configured provider.
`RED_TOOLS`	No	Controls which tools load: unset or all, groups or tool names such as core, core,web, all,-capture_url, auto, or mixed like core,auto.
`RED_API_KEY`	No	API key for a custom OpenAI-compatible endpoint, if needed.
`GROQ_API_KEY`	No	Groq API key for API mode. Default model is qwen/qwen3.8-27b.
`RED_BASE_URL`	No	Base URL for any OpenAI-compatible endpoint, such as Ollama, LM Studio, vLLM, Together or Mistral.
`RED_PROVIDER`	No	Force a provider when several keys are set. One of anthropic, openai, google, groq, openrouter or custom.
`GEMINI_API_KEY`	No	Google Gemini API key for API mode. Default model is gemini-3.6-flash.
`GOOGLE_API_KEY`	No	Alias for the Google Gemini API key for API mode. Default model is gemini-3.6-flash.
`OPENAI_API_KEY`	No	OpenAI API key for API mode. Default model is gpt-6.1-sol.
`RED_MAX_TOKENS`	No	Cap the reply length. Default is 16000.
`ANTHROPIC_API_KEY`	No	Anthropic API key for API mode. Default model is claude-sonnet-5-5.
`OPENROUTER_API_KEY`	No	OpenRouter API key for API mode. Default model is anthropic/claude-sonnet-5.5.

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityMaintained

ResponsivenessNo recent community issues