# Mnemoverse Memory (npm · @mnemoverse/mcp-memory-server)

Hosted memory for AI agents that learns and forgets — one key across Claude, Cursor & ChatGPT.

- Trust score: 67/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.mnemoverse.com`: 38/100, [markdown](https://verifymcp.io/servers/mnemoverse-mcp-memory-server/mcp.md), [page](https://verifymcp.io/servers/mnemoverse-mcp-memory-server/mcp)
- npm · `@mnemoverse/mcp-memory-server`: 67/100 (this document), [markdown](https://verifymcp.io/servers/mnemoverse-mcp-memory-server/mnemoverse-mcp-memory-server.md), [page](https://verifymcp.io/servers/mnemoverse-mcp-memory-server/mnemoverse-mcp-memory-server)

## Channel facts

- Registry: `npm`
- Package: `@mnemoverse/mcp-memory-server`
- Version: `0.5.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 23 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1315 tokens (~146/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add mnemoverse-mcp-memory-server -- npx -y @mnemoverse/mcp-memory-server
```

### Codex

```bash
codex mcp add mnemoverse-mcp-memory-server -- npx -y @mnemoverse/mcp-memory-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mnemoverse-mcp-memory-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@mnemoverse/mcp-memory-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mnemoverse-mcp-memory-server --command npx --arg -y --arg @mnemoverse/mcp-memory-server
```

### Hermes

```yaml
mcp_servers:
  mnemoverse-mcp-memory-server:
    command: "npx"
    args: ["-y", "@mnemoverse/mcp-memory-server"]
```

### Other

```json
{
  "mcpServers": {
    "mnemoverse-mcp-memory-server": {
      "command": "npx",
      "args": [
        "-y",
        "@mnemoverse/mcp-memory-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 67, +47)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 20, +15)

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 5, −22)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 27, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (9)

### `memory_write` (~253 tokens)

Store a long-term memory that persists across sessions AND across every AI tool the user has connected to Mnemoverse (Claude, ChatGPT, Cursor, VS Code) — write once, recall everywhere. Call this PROACTIVELY the moment the user states a preference, makes a decision, or you learn a durable fact (people, roles, project setup, a lesson). Don't wait to be asked. Do NOT use it for transient chatter, secrets, or anything only relevant to the current turn. Behavior: an importance gate may filter low-value writes, so the result tells you whether the memory was stored or filtered. Write `content` as a self-contained statement that still makes sense when recalled out of context.

Input parameters:

- `concepts` (array): Key concepts for linking related memories (e.g. ['deploy', 'friday', 'staging'])
- `content` (string, required): The memory to store as a self-contained statement, e.g. 'User prefers TypeScript strict mode' or 'Decided to deploy the API on Cloudflare Workers (2026-06)'.
- `domain` (string): Namespace to organize memories (e.g. 'engineering', 'user:alice', 'project:acme')

### `memory_read` (~202 tokens)

Search your long-term memory before answering anything that may have come up before — user preferences, past decisions, project setup, people, or earlier context. This memory is shared: it persists across sessions and across every AI tool the user has connected (Claude, ChatGPT, Cursor, VS Code). ALWAYS check here first when you're unsure whether you already know something; no need to call it for general world knowledge you already hold. Returns matches ranked by relevance (semantic similarity plus learned concept associations); each result carries an id you can pass to memory_feedback or memory_delete.

Input parameters:

- `domain` (string): Restrict the search to one domain namespace (e.g. 'project:acme'); omit to search across all domains.
- `query` (string, required): Natural-language description of what you're looking for, e.g. 'database choice for the API' or 'user's preferred testing framework'.
- `top_k` (integer): Max results to return (default: 5)

### `memory_feedback` (~133 tokens)

Report whether memories returned by memory_read were actually helpful. This is a learning signal, not a log: positive feedback raises a memory's ranking so it surfaces faster next time (across all of the user's tools), negative feedback lets it fade. Call it right after you act on (or reject) recalled memories, passing the ids from the memory_read results.

Input parameters:

- `atom_ids` (array, required): IDs of memories to give feedback on (from memory_read results)
- `outcome` (number, required): How helpful was this? 1.0 = very helpful, 0 = neutral, -1.0 = harmful/wrong

### `memory_stats` (~88 tokens)

Get an overview of the stored memory: total count, episodes vs consolidated prototypes, number of learned associations, the list of domains, and average quality scores. This memory is shared across all AI tools the user has connected to Mnemoverse. Use it to orient yourself, to confirm the exact domain name before a delete, or when the user asks what you remember. Read-only — changes nothing.

### `memory_delete` (~112 tokens)

Permanently delete ONE memory by its atom_id — irreversible, the memory is gone for good. Use only when the user explicitly asks to forget something specific, or to correct a fact you stored wrongly. Get the atom_id from a memory_read result. To clear an entire topic at once, use memory_delete_domain instead. Never delete on your own initiative — require an explicit user request.

Input parameters:

- `atom_id` (string, required): The atom_id of the memory to delete (from memory_read results — each item has an id)

### `memory_delete_domain` (~160 tokens)

Permanently delete EVERY memory in one domain — irreversible, and far more destructive than memory_delete. Use only on an explicit user request to wipe a whole topic, e.g. 'forget everything about project X' or 'wipe my benchmark experiments'. First run memory_stats to confirm the exact domain name, then pass it together with confirm=true (a deliberate safety interlock). Never call this speculatively or to 'clean up' on your own — only when the user explicitly asks.

Input parameters:

- `confirm` (boolean, required): Must be exactly true to proceed. Acts as a safety interlock against accidental invocation.
- `domain` (string, required): The domain namespace to wipe (e.g., 'project:old', 'experiments-2025'). Must match exactly.

### `memory_create_room` (~137 tokens)

Create a SHARED memory room — a space you and OTHER people's assistants can both read and write, across Claude/ChatGPT/Cursor. Use when the user wants to share context or collaborate with someone else (e.g. 'make a room for me and Olya'). Returns the room's address; pass that address as the `domain` on memory_write/memory_read to use it. To bring someone in, call memory_invite_to_room next.

Input parameters:

- `description` (string): Optional description of the room.
- `name` (string, required): Room name, unique within your account (e.g. 'me-and-olya').

### `memory_invite_to_room` (~143 tokens)

Mint a one-time invite for a room you own and get a ready-to-forward message. The user sends that message to the person they want to add (any messenger); the recipient opens the link or tells THEIR assistant the code to join. Use after memory_create_room, or whenever the user says 'invite <someone>' to an existing room.

Input parameters:

- `expires_in_days` (integer): Days until the invite expires (default 7).
- `room_id` (string, required): The room's id (room_...), from memory_create_room.
- `scope` (string): Role the invitee gets — 'read' or 'read_write' (default read_write).

### `memory_join_room` (~87 tokens)

Join a shared memory room using an invite code (starts with 'mnvr_'). Use when the user pastes an invite code or says something like 'join room with code ...'. After joining, use the returned address as the `domain` on memory_write/memory_read to read and write the shared room.

Input parameters:

- `code` (string, required): The invite code (mnvr_...).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/mnemoverse-mcp-memory-server/mnemoverse-mcp-memory-server#diagnostics

## Score history

- 2026-08-03: 67
- 2026-08-02: 67
- 2026-08-01: 20
- 2026-07-31: 5
- 2026-07-30: 27
- 2026-07-28: 45
- 2026-07-27: 45

## Links

- npm package: https://www.npmjs.com/package/@mnemoverse/mcp-memory-server
- Socket report: https://socket.dev/npm/package/@mnemoverse/mcp-memory-server
- Repository: https://github.com/mnemoverse/mcp-memory-server
- Website: https://mnemoverse.com/
- Changelog RSS feed: https://verifymcp.io/servers/mnemoverse-mcp-memory-server/mnemoverse-mcp-memory-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/mnemoverse-mcp-memory-server/mnemoverse-mcp-memory-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/mnemoverse-mcp-memory-server/mnemoverse-mcp-memory-server