Skip to main content
Glama
H1an1

mem-universe

by H1an1
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEMORY_TOKENYesThe bearer token used for authentication. Generate with openssl rand -hex 32.
MEM_STORE_REMOTEYesThe git remote URL of your private store repository.

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
searchB

BM25 search across the memory store. Returns ranked {path, score, snippet, type}.

readB

Read a single memory file by store-relative path.

writeA

Write a memory file (also indexes it). Returns {ok, path}.

There are exactly two layers. `path` is store-relative and starts with one:
  - `shared/...`    — the cross-agent knowledge base (skills/tools/lessons/rules)
  - `personal/...`  — the owner's personal space (free-form)

`layer` is OPTIONAL — leave it out and it's inferred from the path. If you do
pass it, the only valid keys are "shared" and "personal".

Layers are SHARED spaces, not per-author: every connected agent reads and
writes the same paths. `author_agent` only records who wrote an entry
(provenance); it does not partition or hide anything. So `personal/` is "the
owner's personal layer", visible to all connected agents — NOT "this agent's
private space". Truly secret material should not be put in this store at all.

`type` is one of skill|tool|lesson|rule|conversation|note (inferred from the
path if omitted). An explicit type="skill" must include the 5 template
sections, each headed in Chinese OR English: 目标/Goal, 何时用/When to use,
前置/Preconditions, 步骤/Steps, 验证/Verify.
deleteC

Delete a memory file. Git keeps history, so it's recoverable. Returns {ok, deleted}.

listC

List entries under a layer (optionally a prefix within it).

put_skillA

Store a runnable skill PACKAGE (a SKILL.md + its scripts/templates) byte-exact under shared/skills//. files maps package-relative paths to text content and MUST include a SKILL.md. Files are stored verbatim — no frontmatter, no template check (unlike write, which is for single markdown notes). The SKILL.md is indexed so search finds the package; any agent can later get_skill to install it. Returns {name, paths, commit}.

To push your local package: read every file under your skills dir (e.g.
~/.claude/skills/<name>/) into `files`, then call this. Text files only (v1).
get_skillA

Fetch a whole skill package as {name, files: {relpath: content}}. To install it, write each file into your local skills dir (e.g. ~/.claude/skills//). Any agent can fetch + run a package; Claude-family agents additionally get native auto-invocation.

list_skillsA

List stored skill packages as [{name, description}] (description from each SKILL.md).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored across 8 tools

Disambiguation5/5

Each tool serves a distinct purpose: file operations (delete, read, write), skill management (get_skill, put_skill, list_skills), and discovery (list, search). No two tools have overlapping functionality.

Naming Consistency4/5

Names are lowercase with underscores for multi-word tools (e.g., get_skill), but single-word names like delete and read break the pattern slightly. Still, the naming is predictable and readable.

Tool Count5/5

8 tools cover core operations for memory files and skills without bloat. The set is well-scoped for the stated purpose.

Completeness4/5

Covers create/read/delete for files and CRUD for skills except delete_skill. Write presumably overwrites, acting as update. Minor gap: no dedicated skill deletion tool.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources