Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_HOSTNoListen address inside the container. Default: 0.0.0.0
MCP_PORTNoListen port inside the container. Default: 8000
ZIM_CHECKNoRun libzim's full checksum verification at startup (reads entire corpus). Default: false
CORPUS_ROOTYesCorpus root directory inside the container (required). Default: /corpus
LOG_QUERIESNoLog search query text (privacy). Default: true
SEARCH_LIMITNoDefault limit for search(). Default: 5
CORPUS_CONFIGYesPath to the corpus manifest (corpus.toml) inside the container (required). Default: /config/corpus.toml
SEARCH_WORKERSNoConcurrent archive searches during fan-out. Default: 8
MAX_FETCH_CHARSNoOutput budget for fetched content. Default: 100000
SEARCH_MAX_LIMITNoHard maximum for search(limit=…). Default: 10
SEARCH_MAX_CONSECUTIVENoDiversity pass: max consecutive results from one library. Default: 2

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