Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
REDIS_URLNoMemorystore/Redis URL for shared cache and rate limits.
NEWSAPI_KEYNoNewsAPI key for news evidence.
SEARXNG_URLNoURL of a self-hosted SearXNG instance for web search evidence.
MODEL_DEVICENoDevice for model inference (cpu or cuda).cpu
BRAVE_API_KEYNoBrave API key for web search evidence.
CUSTOM_DOMAINNoCustom domain for redirects.foresea.ink
SERPER_API_KEYNoSerper API key for web search evidence.
SESSION_SECRETNoLong random string used to sign browser session JWTs.
TAVILY_API_KEYNoTavily API key for web search evidence.
FORESEA_API_KEYNoOptional API key for private deployment auth; forwarded as X-API-Key.
LOCAL_CACHE_MAXNoMax entries in the in-memory fallback cache.1024
GITHUB_CLIENT_IDNoGitHub OAuth client ID.
GOOGLE_CLIENT_IDNoGoogle OAuth web client ID.
SCADS_AI_API_KEYYesAPI key for the hosted model endpoint used by the MCP server.
EXTRACT_CACHE_TTLNoCache TTL (s) for /extract URL fetches.3600
PREDICT_CACHE_TTLNoCache TTL (s) for non-personalised /predict responses.600
EVIDENCE_CACHE_TTLNoCache TTL (s) for evidence retrieval.900
GITHUB_CLIENT_SECRETNoGitHub OAuth client secret.

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/pareelamre/analyzing-llm-rationale'

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