# io.github.MarcelRoozekrans/longterm-memory (npm · longterm-memory-mcp)

A fully local MCP server for long-term memory with semantic search

- Trust score: 0/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

> **Recent critical change**: Known CVEs (2026-11-01). See the changelog below before you install this server.

## Components

- npm · `longterm-memory-mcp`: 0/100 (this document), [markdown](https://verifymcp.io/servers/marcelroozekrans-longterm-memory/longterm-memory-mcp.md), [page](https://verifymcp.io/servers/marcelroozekrans-longterm-memory/longterm-memory-mcp)

## Channel facts

- Registry: `npm`
- Package: `longterm-memory-mcp`
- Version: `1.6.1`
- 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 2026-11-04.

- **Supply Chain Security**: 73/100
  - No malware found by supply-chain analysis.
  - CVE check failed: an unpatched critical CVE affects this package; the score is capped at 0.
  - No install/post-install scripts declared.
  - 61 of 169 dependencies flagged as unhealthy (1 deprecated).
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to MarcelRoozekrans/LongtermMemory-MCP).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 788 tokens (~71/item across 11 items; 11 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 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.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_memory" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.MarcelRoozekrans/longterm-memory MCP server?

io.github.MarcelRoozekrans/longterm-memory runs locally as an npm package, launched with npx -y longterm-memory-mcp. 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 marcelroozekrans-longterm-memory -- npx -y longterm-memory-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "marcelroozekrans-longterm-memory": {
      "command": "npx",
      "args": [
        "-y",
        "longterm-memory-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "marcelroozekrans-longterm-memory": {
      "command": "npx",
      "args": [
        "-y",
        "longterm-memory-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add marcelroozekrans-longterm-memory -- npx -y longterm-memory-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add marcelroozekrans-longterm-memory --command npx --arg -y --arg longterm-memory-mcp
```

### Hermes

```yaml
mcp_servers:
  marcelroozekrans-longterm-memory:
    command: "npx"
    args: ["-y", "longterm-memory-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "marcelroozekrans-longterm-memory": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "longterm-memory-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add marcelroozekrans-longterm-memory -t stdio -c npx -a -y longterm-memory-mcp
```

### Other

```json
{
  "mcpServers": {
    "marcelroozekrans-longterm-memory": {
      "command": "npx",
      "args": [
        "-y",
        "longterm-memory-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-11-01 (score 0, −73)

- [critical regression] Known CVEs: unverified → fail
- [critical regression] Score status: scored → failed
- [functional improvement] Dependency health: unverified → 0.83

### 2026-10-31 (score 73, +73)

- [security regression] Known CVEs: fail → unverified
- [security improvement] Malware scan: unverified → pass
- [functional regression] Dependency health: 0.83 → unverified
- [functional improvement] Score status: failed → scored
- [functional] Package version: 1.6.0 → 1.6.1

### 2026-10-30 (score 0, 0)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 1.5.0 → 1.6.0

### 2026-10-22 (score 0)

First indexed and scored.

## MCP tools (11)

### `save_memory` (~188 tokens)

Save information to long-term memory. The content will be embedded locally and indexed for semantic search. Use this to store facts, decisions, preferences, or any context worth remembering across sessions. Text inside <private>…</private> is removed before storing; content that looks like a secret (tokens, keys, passwords) is rejected.

Input parameters:

- `content` (string, required): The text content to store in memory
- `importance` (number): Importance level 1-10 (default: 5). Higher = more resistant to decay
- `memory_type` (string): Memory category (default: general). Affects decay rate
- `metadata` (object): Optional key-value metadata to attach to this memory (e.g. { "topic": "auth", "project": "api" })
- `tags` (array): Optional tags for categorization (e.g. ["personal", "preference"])

### `search_memory` (~88 tokens)

Search long-term memory using semantic similarity. The query is embedded locally and compared against all stored memories using cosine similarity.

Input parameters:

- `limit` (integer): Maximum number of results to return (default: 5)
- `query` (string, required): Natural language search query describing what you're looking for
- `threshold` (number): Minimum similarity score threshold, 0-1 (default: 0.3)

### `get_all_memories` (~63 tokens)

Retrieve all stored memories, ordered by most recent first. Results are paginated.

Input parameters:

- `limit` (integer): Maximum number of memories to return (default: 50)
- `offset` (integer): Number of memories to skip for pagination (default: 0)

### `update_memory` (~108 tokens)

Update an existing memory. Can modify content (triggers re-embedding), metadata, tags, importance, or memory type.

Input parameters:

- `content` (string): New text content (triggers re-embedding)
- `id` (string, required): The UUID of the memory to update
- `importance` (number): New importance level 1-10
- `memory_type` (string): New memory category
- `metadata` (object): New metadata object
- `tags` (array): New tags array

### `search_by_type` (~60 tokens)

Search memories by category type (e.g. fact, preference, conversation). Returns memories ordered by importance.

Input parameters:

- `limit` (integer): Maximum number of results (default: 20)
- `memory_type` (string, required): The memory type to filter by

### `search_by_tags` (~60 tokens)

Find memories that match any of the provided tags. Returns memories ordered by importance.

Input parameters:

- `limit` (integer): Maximum number of results (default: 20)
- `tags` (array, required): Tags to search for — matches memories containing ANY of these tags

### `search_by_date_range` (~97 tokens)

Find memories created within a specific date range. Use ISO date format.

Input parameters:

- `date_from` (string, required): Start date in ISO format (e.g. "2026-01-01" or "2026-01-01T00:00:00Z")
- `date_to` (string): End date in ISO format (defaults to now)
- `limit` (integer): Maximum number of results (default: 50)

### `delete_memory` (~48 tokens)

Delete a specific memory by its ID. Only delete when the user explicitly requests it or when a memory is confirmed outdated or incorrect.

Input parameters:

- `id` (string, required): The UUID of the memory to delete

### `delete_all_memories` (~32 tokens)

Delete ALL stored memories. This action is irreversible. Only use when the user explicitly asks to clear all memories.

### `memory_stats` (~21 tokens)

Get statistics about the memory store — total count and database location.

### `create_backup` (~23 tokens)

Create a manual backup of the memory database and export all memories as JSON.

## Diagnostics

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

## Score history

- 2026-11-04: 0
- 2026-11-03: 0
- 2026-11-02: 0
- 2026-11-01: 0
- 2026-10-31: 73
- 2026-10-30: 0
- 2026-10-29: 0
- 2026-10-28: 0
- 2026-10-27: 0
- 2026-10-26: 0
- 2026-10-25: 0
- 2026-10-24: 0
- 2026-10-23: 0
- 2026-10-22: 0

## Common questions

### What is the io.github.MarcelRoozekrans/longterm-memory MCP server?

io.github.MarcelRoozekrans/longterm-memory is an MCP server listed in the public MCP registry as io.github.MarcelRoozekrans/longterm-memory. A fully local MCP server for long-term memory with semantic search. This page covers its npm package (longterm-memory-mcp).

### What tools does the io.github.MarcelRoozekrans/longterm-memory MCP server expose?

io.github.MarcelRoozekrans/longterm-memory exposes 11 tools: save_memory, search_memory, get_all_memories, update_memory, search_by_type, and 6 more. Their descriptions and schemas cost roughly 788 tokens of context every time the server is loaded.

### Is the io.github.MarcelRoozekrans/longterm-memory MCP server still maintained?

io.github.MarcelRoozekrans/longterm-memory is still listed as active in the MCP registry. We last reached this channel on 4 November 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 io.github.MarcelRoozekrans/longterm-memory MCP server under?

io.github.MarcelRoozekrans/longterm-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/longterm-memory-mcp
- Socket report: https://socket.dev/npm/package/longterm-memory-mcp
- Repository: https://github.com/MarcelRoozekrans/LongtermMemory-MCP
- Changelog RSS feed: https://verifymcp.io/servers/marcelroozekrans-longterm-memory/longterm-memory-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/marcelroozekrans-longterm-memory/longterm-memory-mcp.json
- HTML version of this page: https://verifymcp.io/servers/marcelroozekrans-longterm-memory/longterm-memory-mcp