Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DOCS_URLSNoDocumentation URLs to scrape, comma-separated for multiple sites. (e.g., https://docs.example.com/)
HTTP_PORTNoPort for HTTP mode (default: 3000, mapped to 3003 on host).3000
TRANSPORTNoTransport mode: stdio (local MCP) or http (remote/Kubernetes). Default is stdio.stdio
SWAGGER_URLSNoSwagger/OpenAPI JSON URLs, comma-separated (optional).
USE_EMBEDDINGSNoEnable semantic search (true) or keyword search (false). Default is true.true
CRAWL_MAX_DEPTHNoMaximum crawl depth (0-3, recommended 2). Default is 2.2
EMBEDDING_PROVIDERNoEmbedding provider: huggingface, openai, or azure. Default is huggingface.huggingface
AUTO_UPDATE_ENABLEDNoEnable scheduled documentation updates (true/false). Default is false.false

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

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/Qvakk/docs-scraper-shell-for-mcp'

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