Tracked packageView full profile for server-memory

MCPSafe.io

Security pre-install checks for MCP servers.

Mostly safe — a couple of notes worth reading.

Compare to another server

npm · server-memory2026.1.26

Item: server-memory
Rating: 4
Author: MCPSafe

Scanned 5/23/2026, 1:57:21 PM·Cached result·Deep Scan·91 rules·View source ↗·How we decide ↗

Judge panel3/5reviewed

0/9tools cleared

84%panel agreement

Per-tool scores in Signals tab

AIVSS Score

2.3/ 10

Low

Severity Breakdown

critical

high

medium

low

MCP Server Information

Packageserver-memory

Version2026.1.26

SourceNPM

LicenseMIT

Publisherjspahrsummers

Package age1y 6m

Stars—

Downloads/wk226.2K

Dependencies1

Homepagehttps://modelcontextprotocol.io

Repositorygit+https://github.com/modelcontextprotocol/servers.git

Findings

2 of 2 findings

medium (2)

2 findings

medium (2)

AIVSS 2.3CVSS 3.5

Package declares an install-time hook (npm postinstall/preinstall/prepare, setup.py cmdclass override, custom setuptools install class, or non-default pyproject build-backend). Anyone installing this package runs the hook. Confirm the hook is necessary and review its contents; prefer shipping a plain library without install-time execution.

Evidence

],
  "scripts": {
    "build": "tsc && shx chmod +x dist/*.js",
    "prepare": "npm run build",
    "watch": "tsc --watch",
    "test": "vitest run --coverage"
  },

Remediation

Prefer libraries that do not require install-time code execution: - Drop `postinstall`/`preinstall`/`prepare` scripts if the work can happen at runtime or build-time instead. - Ship pre-built native binaries rather than compiling via a custom `cmdclass` or `build_ext` override. - For Dockerfiles: replace `RUN curl … | sh` with a pinned download + checksum verification + explicit `RUN` of a named script. - If the hook is unavoidable, document exactly what it does so downstream reviewers

Report false positive

AIVSS 2.3CVSS 3.5

MCP manifest declares tools but no authentication field is present (none of: auth, authorization, bearer, oauth, mtls, apiKey, api_key, basic, token, authToken). Absence is a weak signal — confirm whether the server relies on network-layer or host-level auth, or declare the real mechanism explicitly so reviewers can audit it.

Evidence

# Knowledge Graph Memory Server

A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.

## Core Concepts

### Entities
Entities are the primary nodes in the knowledge graph. Each entity has:
- A unique name (identifier)
- An entity type (e.g., "person", "organization", "event")
- A list of observations

Example:
```json
{
  "name": "John_Smith",
  "entityType": "person",
  "observations": ["Speaks fluent Span

Remediation

Declare a real authentication mechanism in the manifest, matching what the running server actually enforces: - `"auth": "bearer"` with a token scheme documented for callers - `"auth": "oauth"` / `"oauth2": { ... }` for delegated flows - `"apiKey": { "header": "X-API-Key", "prefix": "..." }` - `"mtls": true` when client certificates are required If the server is intentionally unauthenticated (stdio-only, local developer tool, trusted-host network), document the assumption in the manifest via a `"

Report false positive

LLM summary— server-memory:2026.1.26

This package has a solid security posture with a B grade and an 88/100 safety score, posing minimal risk. The two medium-severity findings relate only to server configuration issues, with no critical, high, or low vulnerabilities detected. It’s safe to install, but review the configuration recommendations to further harden the setup.

Signal scores

Publisher identity10

Permissions92

Destructive ops100

LLM consensus100

Typosquat100

Server Configuration100

Secrets & exfil100

Static100

Community47

CVE check100

Package health100

Supply chain92

Injection risks100

LLM judge panel

CVE check

No known CVEs found for this package or its dependencies.

Community trust

Multiple security reports

Security policy: Not found
Advisories: 6

GHSA-vjqx-cfc4-9h6v ↗
Path traversal in git_add allows staging files outside repository boundaries in mcp-server-git
GHSA-5cgr-j3jf-jw3v ↗
Unrestricted git_init tool allows repository creation at arbitrary filesystem locations in mcp-server-git
GHSA-9xwc-hfwc-8w59 ↗
Argument injection in git_diff and git_checkout functions for mcp-server-git allows overwriting local files
GHSA-j22h-9j4x-23w5 ↗
Missing path validation when using --repository flag in mcp-server-git

Scan details

Total findings: 2
Affected tools: 0 / 1
Scan type: Deep Scan
Rules run: 91
LLM consensus score: 100/100
Scanned: 82d ago
Source: NPM

MCP Server Information

Source: NPM
Package: server-memory
Version: 2026.1.26
License: MIT
Publisher: jspahrsummers
Verified: No
Added: 1y 6m ago
Versions: 12
Homepage: https://modelcontextprotocol.io
Repository: git+https://github.com/modelcontextprotocol/servers.git
Ecosystem: Node.js / npm
Downloads/wk: 226.2K
Dependencies: 1

AIVSS Score

2.3/ 10Low

Internal score: 88/100

Severity breakdown

Scan Details

Total findings2

Affected tools0 / 1

LLM consensus score100/100

Scanned82d ago

Scan modeDEEP

SourceNPM

Scan IDpubdeep81d7f3d8055cedbcddec795874

Done

Re-scan Scan another package

Building your own MCP server?

Run this exact engine on your private repo — before users see it on /scan.

Same rules, same LLM judges, same grade. Private scans stay isolated to your account and never appear in the public registry. Required for code your team hasn’t shipped yet.

See plans with Private scans How private scans stay private

2 of 2 findings

medium (2)

2 findings

medium (2)

AIVSS 2.3CVSS 3.5

Evidence

],
  "scripts": {
    "build": "tsc && shx chmod +x dist/*.js",
    "prepare": "npm run build",
    "watch": "tsc --watch",
    "test": "vitest run --coverage"
  },

Remediation

Report false positive

AIVSS 2.3CVSS 3.5

Evidence

# Knowledge Graph Memory Server

A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.

## Core Concepts

### Entities
Entities are the primary nodes in the knowledge graph. Each entity has:
- A unique name (identifier)
- An entity type (e.g., "person", "organization", "event")
- A list of observations

Example:
```json
{
  "name": "John_Smith",
  "entityType": "person",
  "observations": ["Speaks fluent Span

Remediation

Report false positive

20	],
21	"scripts": {
22	"build": "tsc && shx chmod +x dist/*.js",
23	"prepare": "npm run build",
24	"watch": "tsc --watch",
25	"test": "vitest run --coverage"
26	},

1	# Knowledge Graph Memory Server
2
3	A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.
4
5	## Core Concepts
6
7	### Entities
8	Entities are the primary nodes in the knowledge graph. Each entity has:
9	- A unique name (identifier)
10	- An entity type (e.g., "person", "organization", "event")
11	- A list of observations
12
13	Example:
14	```json
15	{
16	"name": "John_Smith",
17	"entityType": "person",
18	"observations": ["Speaks fluent Span