What are the risks of connecting to pypi:n3memorycore-mcp-lite?

Prompt-injection markup found in package source. Overall trust grade F (55/100).

When was pypi:n3memorycore-mcp-lite last audited?

Last checked 2026-06-03; wmcp.sh re-checks it on a schedule for tool drift and rug-pulls.

pypi:n3memorycore-mcp-lite

Item: pypi:n3memorycore-mcp-lite
Rating: 55
Author: wmcp.sh

https://pypi.org/project/n3memorycore-mcp-lite/

55/100 · MCP Trust Grade · checked 1mo ago · MCP 1.9.1

Is the pypi:n3memorycore-mcp-lite MCP server safe to use?

Independent trust grade F (55/100). Prompt-injection markup found in package source. wmcp.sh continuously watches pypi:n3memorycore-mcp-lite for tool drift and rug-pulls. The grade is free and identical whether or not the operator pays.

What it offers — 7 tools · Database

search_memory

save_memory

list_memories

delete_memory

delete_memories_by_session

repair_memory

recall_thread

Spec / packaging20%100

✓ depends on an MCP SDK (mcp/fastmcp)
✓ 7 tool(s) detected in source

Security (OWASP MCP)30%15

⚠ prompt-injection markup in source
scanned 6 source files from GitHub

Maintenance / popularity20%100

published within 90 days
8 releases, 430 downloads/wk

Tool hygiene15%80

9 declared deps
public repo

Transparency / provenance15%85

✓ repo: github.com/NeuralNexusNote/n3mcmcp-lite
✓ Apache License license

Findings

FAILMCP01 Prompt-injection markup found in package source.

INFO Static analysis of PyPI package n3memorycore-mcp-lite@1.9.1 (source: github.com/NeuralNexusNote/n3mcmcp-lite) — stdio server, no remote endpoint. Runtime behavior not measured.

Grade another server

We re-grade pypi:n3memorycore-mcp-lite on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — pypi:n3memorycore-mcp-lite grade F

Share on X Open card image

https://wmcp.sh/mcp/grade/pypi%3An3memorycore-mcp-lite

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade F](https://wmcp.sh/mcp/grade/pypi%3An3memorycore-mcp-lite/badge.svg)](https://wmcp.sh/mcp/grade/pypi%3An3memorycore-mcp-lite)

HTML

<a href="https://wmcp.sh/mcp/grade/pypi%3An3memorycore-mcp-lite"><img src="https://wmcp.sh/mcp/grade/pypi%3An3memorycore-mcp-lite/badge.svg" alt="MCP Trust Grade F · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.