Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LORE_API_URLNoGraphQL endpoint.http://localhost:3030/graphql
LORE_PROJECTNoDefault project slug used when a tool omits project.
LORE_API_TOKENYesThe lore_sk_... API token. Sent as Authorization: Bearer <token>.

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
}

Tools

Functions exposed to the LLM to take actions

NameDescription
lore_startB

Load the team briefing for a project: the area context docs plus recent session captures. The team /start.

lore_captureA

Append an append-only session - project- and user-scoped. A session is one unit of work you did (a ticket / bug / feature); you can have several per day across projects. By default it is a project-level session (no node) - omit node. Optionally pass node to also attach it to an area. The backend only stores it; nothing is synthesized.

lore_adrB

Create or update a Architecture Decision Record node by path (kind: adr).

lore_logC

Create or update a log entry node by path (kind: log).

lore_todoC

Create or update a TODO node by path (kind: todo).

lore_planB

Create or update a plan node by path (kind: plan).

lore_memoryC

Create or update a memory (durable fact/learning) node by path (kind: memory).

lore_treeB

List the folder/doc tree for a project. Optionally scope by parent node or kind.

lore_contextA

Read or write an area's context document (a context-kind node). Omit body to FETCH the context at a path. Pass body to WRITE it directly as authored content - this is an authored doc, it does NOT run synthesis. Use this for importing/editing hand-written context.md files; the capture flow is what derives context from sessions.

lore_searchB

Search nodes in a project by path substring (best-effort).

lore_projectsA

List every organization and project you can access (personal ones and orgs you've joined), grouped by organization. Your API token is personal - it spans all your orgs. Use this to pick or confirm which project a repo should be linked to (see /lore:init).

lore_create_projectA

Create a new project in one of your organizations. Pass the organization slug (from lore_projects) and a name; the slug is derived from the name (lowercase, dashes) unless you pass an explicit slug. Used by /lore:init when the user chooses to create a new project.

lore_deleteA

Delete a node (and its children) by path or id. Irreversible - use to clean up mistaken or stale nodes.

lore_moveA

Move or rename a node to a new path (and optionally a new parent), by path or id. Cascades child paths.

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 14 tools

Disambiguation5/5

Each tool targets a distinct node kind or action (create/update for specific types, delete, move, search, list). Even lore_context combines read and write but is clearly described based on body presence. No two tools serve the same purpose.

Naming Consistency4/5

All tools share the 'lore_' prefix. Most use a single noun or verb (adr, capture, context, delete, log, memory, move, plan, search, start, todo, tree) but some are two-word verbs (create_project) and a few are nouns used as verbs (adr, context, log, memory, plan, todo, tree). The pattern is consistent across the set but not perfectly verb_noun.

Tool Count5/5

With 14 tools covering node lifecycle (create/update for 6 types, delete, move, search, list, projects, startup briefing), the count is well-scoped for a knowledge management server. Each tool serves a clear purpose without being excessive.

Completeness4/5

Core CRUD is covered for all node types via create/update, delete, and move. Search and tree listing provide access. Minor gaps include no dedicated 'get single node by path' tool for all types, but search and context fetch cover retrieval. Overall surface is sufficient for the domain.

Maintenance

ActivityInactive
ResponsivenessNo issues