Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FAVORITESNoFilter resources by favorites onlytrue
LOG_LEVELNoLog level: DEBUG, INFO, WARNING, ERRORINFO
STASH_API_KEYYesRequired API key (mandatory)
STASH_ENDPOINTNoStash server endpointhttp://localhost:6969
STASH_CONNECT_RETRIESNoInitial connection retries3
STASH_CONNECT_DELAY_SECONDSNoDelay between retries (seconds)1.5

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_performer_infoB

Return detailed information for a single performer

get_all_performersA

Return a list of performers with advanced filtering options

get_all_scenesB

Return all scenes from Stash with advanced filtering options

get_all_scenes_from_performerA

Return all scenes for a given performer

health_checkA

Return basic health/connectivity information for the MCP server

advanced_performer_analysisC

Advanced performer analysis with progress reporting and contextual logging

batch_performer_insightsC

Generates insights for multiple performers with detailed progress

Prompts

Interactive templates invoked by user choice

NameDescription
analyze-performerGenerates a complete analysis of a performer including statistics, popular scenes, frequent tags and similar recommendations
library-insightsGenerates insights about the library: trends, metadata gaps, organization recommendations
recommend-scenesBased on user preferences, recommends specific scenes with explanation of why each recommendation
discover-performersDiscover performers based on specific user criteria

Resources

Contextual data attached and managed by the client

NameDescription
All performersList of all favorite performers in the Stash database
Performers StatisticsStatistical summary of all performers in the database
All studiosList of all favorite studios in the Stash database
Studios StatisticsStatistical summary of all studios in the database
All tagsList of all favorite tags in the Stash database
Tags StatisticsStatistical summary of all tags in the database

TDQS

C2.9/5.0

Scored across 7 tools

Disambiguation4/5

Most tools have distinct purposes, but 'advanced_performer_analysis' and 'batch_performer_insights' overlap in intent (both analyze performers). The difference between 'analysis' and 'insights' is unclear, causing potential confusion.

Naming Consistency3/5

Tool names mix patterns: some start with 'get_' (consistent verb_noun), while others use descriptive nouns like 'advanced_performer_analysis' or 'health_check'. This inconsistency in verb usage reduces predictability.

Tool Count5/5

7 tools is well within the ideal 3-15 range for a focused server. Each tool serves a clear role in querying performer and scene data, without unnecessary bloat.

Completeness2/5

The toolset lacks fundamental operations: no way to get details of a single scene, no search across entities, and no create/update/delete capabilities. This leaves significant gaps for typical management tasks.

Maintenance

ActivityInactive
ResponsivenessNo issues