Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

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
memshelf_shelveA

Offload one closed topic to the shelf as a durable, indexed episode — redaction, digest contract and git commit included. Derived files are not written here — they are rendered by memshelf_rebuild or the shelf's bot. Details: docs/tools.md.

memshelf_lint_digestA

Check a digest against the contract while it is still being written — the same validator memshelf_shelve runs, writing nothing. strict turns warnings into failures.

memshelf_recallA

Fetch a shelved episode by id, or one ## Section of it, as a data envelope. Prefer the section when it answers the question.

memshelf_indexA

Return the shelf INDEX — the small recall entry point. Read it before answering anything about past work, then recall only what you need.

memshelf_searchA

Grep the shelf for episodes matching every query token; returns addresses and snippets. Use when the episode id is unknown.

memshelf_statsA

Report the shelf's token economy: standing cost vs shelved mass, claimed compression, realized savings from logged recalls.

memshelf_adviseA

Report what your context window is made of and what you could put down — breakdown plus ranked proposals; writes nothing. Pass your window's occupants (label, size, live or not); with none it reports the shelf alone.

memshelf_initB

Create (or top up) a memory shelf: layout, categories, INDEX preamble, POLICY.md, shelf.yml. Idempotent; never overwrites existing files.

memshelf_rebuildA

Regenerate the derived files (ledger.tsv, .meta.json, INDEX.md, stats.svg) from the episodes; check=true only reports drift. Hand-run it only on a shelf whose bot is not rendering.

memshelf_rollupB

Archive a period's episodes behind one digest-of-digests you write, shrinking INDEX; nothing is deleted. Not the answer to index-bloat.

memshelf_purgeA

Drop episodes past retain_until, then reindex. Dry run unless apply=true; removes working-tree files only, git history keeps them.

memshelf_resolveA

Settle the two-writers-on-parallel-branches conflict: union derived rows, rebuild INDEX, run doctor. Episode conflicts are reported, never auto-merged; safe outside a conflict too.

memshelf_doctorA

Diagnose shelf integrity: episode schema, digest contract at rest, leaked secrets, ledger consistency, INDEX budget. Read-only; fixes nothing. check_remote adds the network probe for a public remote.

memshelf_importA

Retro-shelve an exported dialog without pulling it through context: discover lists conversations by content markers, extract writes one cleaned conversation to a working file for segmenting and shelving.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4/5.0

Scored across 14 tools

Disambiguation5/5

Each tool targets a clearly distinct operation within the memory-shelf lifecycle: reading (index, recall, search), writing (shelve, import), diagnostics (lint_digest, doctor), maintenance (rebuild, rollup, purge, resolve), and insights (stats, advise). Potential overlaps like lint_digest vs. doctor or rebuild vs. resolve are explicitly differentiated by scope and timing in the descriptions.

Naming Consistency5/5

All 14 tools consistently use the memshelf_ prefix and lower snake_case. The action/artifact naming is predictable across the set, even when a few names are noun-like (stats, doctor) rather than purely verb_noun.

Tool Count5/5

With 14 tools, the server sits in the well-scoped 3-15 range and covers a full lifecycle without obvious filler. Each tool maps to a distinct phase or concern of managing a memory shelf.

Completeness4/5

The surface covers initialization, creation, import, retrieval, search, metrics, validation, rebuild, rollup, retention purge, conflict resolution, and diagnosis. Minor gaps remain, such as no direct per-episode edit, manual delete, or export operation, though retention and rollup mitigate deletion and archival needs.

Maintenance

ActivityActive
ResponsivenessSlow