# Mneme Memory (npm · mneme-memory)

Cross-session memory for AI coding agents via six tools; local-first SQLite store.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-26

## Components

- npm · `mneme-memory`: 65/100 (this document), [markdown](https://verifymcp.io/servers/modusensus-mneme-memory/mneme-memory.md), [page](https://verifymcp.io/servers/modusensus-mneme-memory/mneme-memory)

## Channel facts

- Registry: `npm`
- Package: `mneme-memory`
- Version: `0.1.1`
- 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 2026-09-26.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 48/100
  - 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 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1207 tokens (~201/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 97% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "memory_delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Mneme Memory MCP server?

Mneme Memory runs locally as an npm package, launched with npx -y mneme-memory. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add modusensus-mneme-memory -- npx -y mneme-memory
```

### Cursor

```json
{
  "mcpServers": {
    "modusensus-mneme-memory": {
      "command": "npx",
      "args": [
        "-y",
        "mneme-memory"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "modusensus-mneme-memory": {
      "command": "npx",
      "args": [
        "-y",
        "mneme-memory"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add modusensus-mneme-memory -- npx -y mneme-memory
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add modusensus-mneme-memory --command npx --arg -y --arg mneme-memory
```

### Hermes

```yaml
mcp_servers:
  modusensus-mneme-memory:
    command: "npx"
    args: ["-y", "mneme-memory"]
```

### Netclaw

```json
{
  "McpServers": {
    "modusensus-mneme-memory": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mneme-memory"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add modusensus-mneme-memory -t stdio -c npx -a -y mneme-memory
```

### Other

```json
{
  "mcpServers": {
    "modusensus-mneme-memory": {
      "command": "npx",
      "args": [
        "-y",
        "mneme-memory"
      ]
    }
  }
}
```

## 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.

### 2026-09-25 (score 65, 0)

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

### 2026-09-23 (score 65)

First indexed and scored.

## MCP tools (6)

### `memory_save` (~348 tokens)

Persist one memory entry for future sessions (user preferences, project state, decisions). Call this when the user states a durable preference, a project decision is made, or a lesson is learned. Merges into an existing entry of the same type when the title matches.

Input parameters:

- `agent_scope` (string): Optional explicit agent-scope declaration (issue #170): 'global' or '*' makes this memory visible to every agent; any other value narrows it to that label. Overrides the automatic carrier label for t…
- `content` (string, required): Memory body
- `importance` (integer): 1-5; >= threshold auto-injects into future sessions
- `occurred_at` (string): Optional ISO-8601 instant the remembered event happened (differs from write time). Invalid values are ignored.
- `sensitivity` (string): Optional sensitivity label (free-form, e.g. personal). Same-title entries with different sensitivity stay separate instead of merging.
- `source` (string): Optional provenance
- `tags` (array): Optional tags
- `title` (string, required): Short unique title
- `type` (string, required): preference=user profile; project=project knowledge/state; decision=key decision; history=conversation summary; rejected_solution=rejected/abandoned implementation approach; pitfall=debugging lesson (…
- `workspace_scope` (string): Optional explicit workspace-scope declaration: 'global' or '*' makes this memory visible in every workspace; any other value narrows it to that label. Overrides the automatic carrier label for this w…

### `memory_search` (~312 tokens)

Search the cross-session memory store for past context (solved problems, user preferences, project decisions). IMPORTANT: relevant cross-session memories are already injected into your context every turn — only call this when the injected memory block does NOT contain what you need, or you need to look something specific up. Substring-matches title/content/tags, and augments results with semantic (vector) recall + optional rerank when an embeddings provider is configured. Returns matching entries with source and timestamps.

Input parameters:

- `limit` (integer): Max results (default 20)
- `mode` (string): auto (default) = keyword hits first + vector fill when enabled; keyword = text only; vector = semantic recall first (falls back to keyword); hybrid = vector leads, keyword fills remaining slots
- `occurred_from` (string): Optional ISO date/timestamp lower bound on when the remembered event happened (occurred_at, falling back to created_at). Date-only values are inclusive from that day's 00:00Z.
- `occurred_to` (string): Optional ISO date/timestamp upper bound on occurred_at. Date-only values are inclusive through that day's 23:59:59.999Z.
- `query` (string, required): Search text; substring match over title/content/tags
- `rerank` (boolean): Run cross-encoder rerank over candidates when a local reranker is configured (default true)
- `semantic` (boolean): Shorthand: enable semantic (vector) recall (same as mode=vector when true)

### `memory_list` (~206 tokens)

List memory entries by type, high-importance first, then newest, paginated. Set include_archived=true to also list archived (hidden) entries so they can be located and restored.

Input parameters:

- `include_archived` (boolean): Include archived (hidden) entries so they can be found and restored (default false)
- `limit` (integer): Page size (default 50)
- `occurred_from` (string): Optional ISO date/timestamp lower bound on when the remembered event happened (occurred_at, falling back to created_at). Date-only values are inclusive from that day's 00:00Z.
- `occurred_to` (string): Optional ISO date/timestamp upper bound on occurred_at. Date-only values are inclusive through that day's 23:59:59.999Z.
- `offset` (integer): Page offset (default 0)
- `type` (string): Filter by type; omit for all. 'document' (#230) = agent-registered document pointer rows

### `memory_get` (~41 tokens)

Fetch one memory entry by ID and return its full content as text. Use after memory_list to read a specific entry.

Input parameters:

- `id` (string, required): Memory id

### `memory_update` (~216 tokens)

Modify an existing memory entry (title, content, type, tags, importance).

Input parameters:

- `agent_scope` (string): Optional explicit agent-scope correction (issue #170): 'global' or '*' widens visibility to every agent; any other value narrows it to that label. Omit to keep the current agent scope. Recorded as an…
- `content` (string): New content
- `id` (string, required): Memory id
- `importance` (integer): 1-5
- `reason` (string): Optional context for the correction (what the user actually said/wanted), recorded for reflection
- `tags` (array)
- `title` (string): New title
- `type` (string): New type
- `workspace_scope` (string): Optional explicit workspace-scope correction: 'global' or '*' widens visibility to every workspace; any other value narrows it to that label. Omit to keep the current workspace scope. Recorded as an…

### `memory_delete` (~24 tokens)

Permanently delete a memory entry.

Input parameters:

- `id` (string, required): Memory id

## Diagnostics

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

## Score history

- 2026-09-26: 65
- 2026-09-25: 65
- 2026-09-24: 65
- 2026-09-23: 65

## Common questions

### What is the Mneme Memory MCP server?

Mneme Memory is an MCP server listed in the public MCP registry as io.github.modusensus/mneme-memory. Cross-session memory for AI coding agents via six tools; local-first SQLite store. This page covers its npm package (mneme-memory).

### Is the Mneme Memory MCP server safe to use?

Mneme Memory scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 26 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Mneme Memory MCP server expose?

Mneme Memory exposes 6 tools: memory_save, memory_search, memory_list, memory_get, memory_update, memory_delete. Their descriptions and schemas cost roughly 1,147 tokens of context every time the server is loaded.

### Is the Mneme Memory MCP server still maintained?

Mneme Memory is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Mneme Memory MCP server under?

Mneme Memory declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/mneme-memory
- Socket report: https://socket.dev/npm/package/mneme-memory
- Repository: https://github.com/slow-stack/mneme
- Changelog RSS feed: https://verifymcp.io/servers/modusensus-mneme-memory/mneme-memory.xml
- Changelog JSON feed: https://verifymcp.io/servers/modusensus-mneme-memory/mneme-memory.json
- HTML version of this page: https://verifymcp.io/servers/modusensus-mneme-memory/mneme-memory