Skip to main content
Glama
X1pheR

QMD MCP

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
INDEX_PATHNoQMD index database./data/index.sqlite
QMD_FORCE_CPUNoSet to 1 to disable acceleration probing and force CPU use.0
QMD_HTTP_HOSTNoHTTP listen address inside the container.0.0.0.0
QMD_HTTP_PORTNoHTTP listen port.8181
QMD_CONFIG_PATHNoQMD collection configuration file./config/index.yml
QMD_EMBED_PARALLELISMNoOptional QMD embedding parallelism override.
QMD_DEFAULT_COLLECTIONNoDefault collection for start_embed; otherwise the first configured collection is used.
QMD_EMBED_MAX_BATCH_MBNoDefault maximum explicit embedding batch size in MiB; accepted range 1-128.16
QMD_SOURCE_RELATIVE_ROOTNoOptional common source root. When set, query results include exact, collision-safe source_relative_path values relative to this root.
QMD_EMBED_MAX_DURATION_MSNoMaximum embedding session length; accepted range 60000-7200000 ms.3600000
QMD_EMBED_MAX_DOCS_PER_BATCHNoDefault maximum documents per explicit embedding batch; accepted range 1-32.8
QMD_REFRESH_INTERVAL_MINUTESNoScheduled index-refresh interval; refresh never starts embedding. 0 disables it, maximum 1440.15
QMD_REFRESH_INITIAL_DELAY_SECONDSNoDelay before the first scheduled refresh; accepted range 0-3600.120

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