Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TZNoTimezone used for the summary's timestamp. Convenience for containers, whose default is UTC. Example: America/Sao_Paulo.
MODELNoName of the model to use. Empty means use the server default model (the one already loaded).
MCP_HOSTNoListening interface in --http mode. Warning: changing to 0.0.0.0 exposes the server without authentication.127.0.0.1
MCP_NAMENoName the server announces during the MCP handshake.web-search
MCP_PORTNoListening port in --http mode.8765
LOG_LEVELNoLog level: DEBUG, INFO, ERROR. INFO logs info and error; DEBUG shows each search, each URL read, and the assembled dossier. Log always goes to stderr.INFO
EXTRA_BODYNoRaw JSON merged into the /chat/completions payload for provider-specific parameters. Invalid JSON crashes the server at boot.
SEARXNG_URLNoBase URL of your SearXNG instance. It must have JSON format enabled.http://localhost:8886
MCP_TRANSPORTNoTransport used when --http is not passed. Either stdio or http.stdio
MODEL_API_KEYNoSent as 'Authorization: Bearer <value>'. Local servers usually ignore it; paid providers require the real key.not-needed
MODEL_TIMEOUTNoTimeout in seconds for each LLM call. Large models on CPU may need more.120
SCRAPER_LIMITNoCharacter limit for extracted text in read_url. Empty means the whole page. Does not affect research_web.
MODEL_BASE_URLNoBase URL of an OpenAI-compatible API, without the /chat/completions suffix. Works with llama.cpp, vLLM, Ollama, OpenAI, etc.http://localhost:8200/v1
SCRAPER_TIMEOUTNoTimeout in seconds for downloading each page. Deliberately low: a slow page should not hold up the entire research.6
SEARXNG_TIMEOUTNoTimeout in seconds for each SearXNG query.10
EVAL_JUDGE_MODELNoModel used as judge in the eval. Pointing to a different model than the one that wrote the summary makes the evaluation much less lenient.
SEARXNG_LANGUAGENoLanguage passed to the search. For English, use en-US.pt-BR
MODEL_TEMPERATURENoTemperature for LLM calls. 0 because the task is to summarize sources, not create.0
RESEARCH_MAX_WAVESNoCap on read attempts before giving up. Without it, a bad sequence of links would sweep through the entire reserve and spike latency.4
RESEARCH_POOL_SIZENoReserve of candidate links. Dead, blocked, or text-less links do not use a budget slot; the next in reserve takes their place.20
SEARXNG_CATEGORIESNoSearXNG categories, comma-separated, passed through raw.general,news
EXTRA_SYSTEM_PROMPTNoText appended to the end of the system prompt in every call.
RESEARCH_PAGE_CHARSNoCharacter limit per page in the research_web dossier. Prevents a single outlier page from blowing the context window.25000
SEARXNG_MAX_RESULTSNoNumber of results requested per search. The research_web tool makes multiple searches, so this is the per-search cap, not the total.10
MODEL_CONTEXT_TOKENSNoContext window of the model. Must match the --ctx-size used when starting the server.65536
MODEL_RESERVE_TOKENSNoHow much of the context window is reserved for non-dossier content. The dossier budget is MODEL_CONTEXT_TOKENS - MODEL_RESERVE_TOKENS.4096
RESEARCH_PAGE_BUDGETNoNumber of pages that enter a research dossier, across all searches. Main quality vs latency control.5
MCP_CORS_ALLOW_ORIGINSNoAllowed origins for CORS in --http mode, comma-separated. Only matters for browser-based clients (e.g., MCP Inspector).*

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

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/fabio-barboza/web_search_mcp'

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