# MCP Server Environment Variables
# GitHub Personal Access Token (required for higher rate limits)
# Create one at https://github.com/settings/tokens
# Needs at least 'public_repo' and 'read:packages' scopes
GITHUB_TOKEN=
# Server configuration
PORT=8000
HOST=0.0.0.0
# Vector database settings
INDEX_FILE=data/faiss_index.bin
EMBEDDING_MODEL=all-MiniLM-L6-v2
# LLM API settings for RAG integration
OPENAI_API_KEY=
LLM_API_URL=https://api.openai.com/v1/chat/completions
LLM_MODEL=gpt-4.5
# Alternatively, you can use other API providers by changing the URL and model
# For example, for Azure OpenAI:
# LLM_API_URL=https://your-resource.openai.azure.com/openai/deployments/your-deployment/chat/completions?api-version=2023-05-15
# Or for Anthropic Claude:
# LLM_API_URL=https://api.anthropic.com/v1/messages
# LLM_MODEL=claude-3-sonnet-20240229
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/ProbonoBonobo/sui-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server