Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PCG_LM_MODELYesModel identifier for Qwen (default qwen/qwen3-14b)
PCG_LM_API_KEYYesAPI key for LM Studio (placeholder accepted if authentication disabled)
PCG_LM_BASE_URLYesBase URL for the LM Studio local server (default http://127.0.0.1:1234/v1)
PCG_TRIAGE_MAX_CHARSYesMaximum characters for triage (default 24000)

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": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_sourcesA

List enabled sources and whether each is ready.

searchB

Search selected sources. Returns bounded snippets with provenance and stable IDs.

search_insightsA

Search locally generated keep-only summaries. Use record_id with fetch to inspect evidence.

get_document_memoryB

Get a compact overview. Sections are excluded by default and always strictly capped.

search_document_memoryB

Search detailed page-cited memories. Returns at most 10 bounded section summaries.

fetch_document_sectionA

Fetch one exact detailed memory section returned by search_document_memory.

fetchA

Fetch one exact item returned by search. Never accepts raw paths or URLs.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.7/5.0

Scored across 7 tools

Disambiguation4/5

The tools target distinct resources (sources, insights, document memory, sections) with clear action verbs. Search and search_document_memory could be confused, but descriptions specify different targets, making the separation mostly clear.

Naming Consistency4/5

All tool names use snake_case and follow a mostly predictable verb_noun pattern (list_sources, search_insights). A few names like 'search' and 'fetch' lack an explicit object, which creates minor inconsistency, but the style is uniform.

Tool Count5/5

With 7 tools, the count is well within the ideal range and each tool seems purposefully designed to cover a distinct operation in the search/retrieval workflow, earning its place.

Completeness4/5

The set covers listing sources, searching multiple data types, and fetching specific items or sections, which is complete for a read-only retrieval system. A minor gap is the lack of a way to browse all memory sections without searching, but it's not a major dead end.

Maintenance

ActivitySlowing
ResponsivenessNo issues