Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_MODELNoModel override for OpenAIgpt-4o
OPENAI_API_KEYNoAPI key for OpenAI
ANTHROPIC_MODELNoModel override for Claudeclaude-sonnet-4-6
PERPLEXITY_MODELNoModel override for Perplexitysonar-pro
ANTHROPIC_API_KEYNoAPI key for Anthropic/Claude
PERPLEXITY_API_KEYNoAPI key for Perplexity

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
ask_claudeA

Send a prompt to Claude (Anthropic). Optionally attach a local file — code, text, image, or PDF — for Claude to read and include in its analysis. Use this when you want Claude's perspective on a question, piece of code, document, or design.

ask_codexB

Send a prompt to OpenAI (GPT-4o by default). Optionally attach a local file. Use this when you want a second opinion on code, an alternative implementation, or OpenAI's perspective on an architecture or design decision.

ask_perplexityA

Send a research question to Perplexity for a web-grounded answer with citations. Text and code files can be attached. Images and PDFs cannot (Perplexity has no vision API). Use this for current information, documentation lookups, or questions that benefit from live web search.

brokerA

Send a prompt to multiple AIs in parallel and receive a synthesized comparison. Attach a file to have all selected AIs analyse the same document, image, or code. Perplexity only receives text/code files; images and PDFs are forwarded to Claude and OpenAI only. When synthesize is true (the default), Claude produces a final summary identifying agreements, differences, and a recommended course of action.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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/JRWoodcock/modelmux'

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