Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_API_KEYNoAPI key for real model answers. Optional if using deterministic fake backends.
STIGMERGY_REPOYesPath to the knowledge repository (git checkout).

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
search_brainA

Search ACL-visible team knowledge with hybrid ranking: the most similar pages, not every match. To enumerate a kind, a period, or a connection, use list_pages.

read_pageA

Read one ACL-visible wiki page; a search hit's fragment (path#n) reads that part of a long page with its neighbours.

list_pagesA

List every visible page that matches, 50 per call: exhaustive, unlike search_brain, which returns only the most similar pages. Use it for "all", "every", "which", a period, or everything connected to a page. Filters combine: type (note, concept, entity, project, source), entity_type (person, organization, product, tool, repository, place), layer (one layer you may read), since/until (YYYY-MM-DD; a page matches when a source it cites occurred in the range, a source on its own date), links_to (a page path, or an entity title or alias: the pages linking it), each applied to the page as you see it. sort is recent (latest source first), oldest, or title; pass the returned next as cursor with the same filters.

describe_entityB

Describe one entity page and the ACL-visible pages that link it.

askB

Answer from ACL-visible team knowledge with citations.

brain_submitA

Submit exactly one text value, local file path, or URL to the team wiki.

audience names the one layer the capture files in. Omitted, Stigmergy chooses among your own layers by their descriptions, or files in your default layer when unsure; it never chooses public. The receipt reports layer, layer_decision, and probabilities when a choice was weighed. An explicit resolution_of target remains subject to the cloud writer's evidence and ACL gates.

brain_submissionsA

List queued, processing, landed, or failed submissions.

brain_deleteC

Queue an authorized explicit page or source deletion.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.4/5.0

Scored across 8 tools

Disambiguation4/5

search_brain vs list_pages is explicitly disambiguated (similar vs exhaustive), and ask vs search_brain are distinguished (synthesis vs retrieval). describe_entity overlaps somewhat with read_page and list_pages, but the entity-focused framing keeps it mostly distinct.

Naming Consistency3/5

Names mix a brain_ prefix (brain_delete, brain_submissions, brain_submit), a _brain suffix (search_brain), and bare verbs/nouns (read_page, list_pages, describe_entity, ask). Readable, but no single predictable pattern, and brain_submit vs brain_submissions invites confusion.

Tool Count5/5

Eight tools is a well-scoped set for a knowledge-wiki server: retrieval (search, list, read, ask, describe), ingestion (submit), deletion, and submission tracking. Each tool earns its place.

Completeness3/5

Read/search/list/submit/delete are covered, but there is no update or edit operation for an existing page, and no explicit layer/ACL management despite layers being central to capture. These gaps will force agents into delete-and-resubmit or other workarounds.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues