Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RUST_LOGNoLog level filterinfo
BIND_ADDRNoHTTP server bind address0.0.0.0:3000
FB_COOKIENoCookie header for facebook.com
LLM_MODELNoModel name sent in requestsQwen3.5-4B-Q4_K_M
EXA_API_KEYNoExa API key — used for academic profile (empty = disabled)
LLM_API_KEYNoSet to sk-... for OpenAIno-key-needed
SEARXNG_URLNoSearXNG instance URLhttp://localhost:4000
LLM_BASE_URLNoAny OpenAI-compatible endpointhttp://localhost:8080/v1
ADZUNA_APP_IDNoAdzuna API app ID (job search) — free at developer.adzuna.com
BRAVE_API_KEYNoBrave Search API key (empty = disabled; default fallback for all profiles)
ADZUNA_APP_KEYNoAdzuna API key
ADZUNA_COUNTRYNoAdzuna country code (us, gb, de, fr, …)us
EMBED_BASE_URLNoTEI embed endpoint (e.g. http://localhost:8081)
LLM_FAST_MODELNoModel name for fast LLMQwen3.5-4B-Q4_K_M
LLM_MAX_TOKENSNoMax tokens per LLM call4096
MAX_PAGE_CHARSNoMax characters extracted per page8000
TAVILY_API_KEYNoTavily API key — used for news profile (empty = disabled)
TWITTER_COOKIENoCookie header for twitter.com / x.com
DEDUP_THRESHOLDNoCosine similarity cutoff for deduplication0.92
LINKEDIN_COOKIENoCookie header for linkedin.com
LLM_FAST_STAGESNoPipeline stages routed to fast LLMplanner,summarizer,publisher
LLM_TEMPERATURENoGeneration temperature0.3
RERANK_BASE_URLNoTEI rerank endpoint (e.g. http://localhost:8082)
INSTAGRAM_COOKIENoCookie header for instagram.com
LLM_FAST_API_KEYNoFast LLM API key; empty = inherit LLM_API_KEY
MIN_TEXT_DENSITYNoMinimum text/HTML density ratio0.05
LLM_FAST_BASE_URLNoFast LLM endpoint; empty = use heavy backend
MIN_CONTENT_WORDSNoMinimum word count per page100
MAX_SEARCH_QUERIESNoSub-questions the planner generates4
LLM_FAST_MAX_TOKENSNoMax tokens for fast model4096
MAX_SOURCES_PER_QUERYNoPages scraped per query4
RERANK_QUALITY_WEIGHTNoContent quality weight0.1
STRIP_THINKING_TOKENSNoStrip <think>...</think> from Qwen3 responsestrue
RERANK_AUTHORITY_WEIGHTNoDomain authority weight0.2
RERANK_RELEVANCE_WEIGHTNoCross-encoder score weight0.7
SEARCH_RESULTS_PER_QUERYNoResults fetched per sub-question8

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/mareurs/researcher'

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