npcpy

MCP server · GitHub · ★ 1.5k · graded 2026-10-22Source linked

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

No outside reports on file

This library accesses files and models on your system and may process sensitive text data, so only use it with non-confidential data and review any external models before loading them.

Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Npcpy helpful?

What it can access

Local filesNo local folder access notedLOW
Command executionNo shell command runner notedLOW
Network reachConnects to outside service APINOTED
CredentialsRequires API key or tokenREVIEW
Package sourceGitHub (NPC-Worldwide/npcpy)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/NPC-Worldwide/npcpy ↗

All setup options ↓

Check this skill Watch it in my stack Compare README badge View project

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-22.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Npcpy

A Python library for natural language processing (NLP), large language models, AI agents, machine learning, and knowledge graphs. It appears to provide tools for researchers and developers building AI systems that understand and work with text and multiple types of data.

Who it’s for

AI researchers, machine learning engineers, and developers building NLP applications or multi-modal AI systems. Teams working on knowledge graphs or AI agent projects may find it useful.

Alternatives

spaCy: Mature open-source NLP library with smaller scope, good for standard text processing. - Hugging Face Transformers: Popular library for pre-trained language models and multi-modal AI. - LLaMA.cpp: Lightweight alternative for running large language models locally with minimal dependencies.

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README at https://github.com/NPC-Worldwide/npcpy (opens external site) for installation and configuration instructions, as setup varies by use case.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

34/100

GitHub stars: 1.5k
Listing last refreshed: 2026-10-30

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

File and data access: The library processes text files and machine learning models, which could expose sensitive documents if pointed at private data. - Model injection: Malicious code hidden in third-party models or training data could execute through the library's model loading features. - API key exposure: If used to call external LLM APIs, hardcoded credentials in scripts could leak authentication tokens. - Dependency chain: Python dependencies bundled with the library might contain vulnerabilities or malicious code from upstream packages. - Output leakage: Processed text or model outputs sent to logging, databases, or cloud services could inadvertently share confidential information.

How to lower the risk

Least-privilege permissions

Run the library under a user account with minimal file access.
Restrict which directories it can read or write.

Network isolation

Run on an air-gapped machine if processing highly sensitive text.
Monitor outbound network connections for unexpected API calls.

Monitoring

Log all data processed and outputs generated.
Check for unexpected model downloads or file access.

Red flags to watch for

Library suddenly downloading large unknown model files.
Error messages revealing file paths or system details.
Requests to load models from untrusted URLs.

Questions

How do I install Npcpy?

Npcpy does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/NPC-Worldwide/npcpy.

Are there security reports about Npcpy?

No reports found for this package in our research (last checked 2026-10-30). Npcpy currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include file and data access.

Is Npcpy actively maintained?

Npcpy has 1.5k GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/NPC-Worldwide/npcpy before pinning it in production.

What are alternatives to Npcpy?

Notable alternatives to Npcpy include spaCy (Mature open-source NLP library with smaller scope, good for standard text processing. - **Hugging Face Transformers**: Popular library for pre-trained language models and multi-modal AI. - **LLaMA.cpp**: Lightweight alternative for running large language models locally with minimal dependencies). You can also compare Npcpy side by side with other MCP servers in the Related tools section on this page.

Maintain or use Npcpy? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

GitHub README Markdown:

markdown

[![AgentArmorHQ Risk Grade for Npcpy](https://agentarmorhq.com/api/badge/npc-worldwide-npcpy)](https://agentarmorhq.com/skills/npc-worldwide-npcpy)

HTML embed:

html

<a href="https://agentarmorhq.com/skills/npc-worldwide-npcpy"><img src="https://agentarmorhq.com/api/badge/npc-worldwide-npcpy" alt="AgentArmorHQ Risk Grade for Npcpy" height="20" /></a>

Terminal check:

terminal

curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "npc-worldwide-npcpy"

Share with your security lead

Need sign-off to use npcpy? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: npcpy
- **Listing URL:** https://agentarmorhq.com/skills/npc-worldwide-npcpy
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.5k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (NPC-Worldwide/npcpy)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/NPC-Worldwide/npcpy
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type: App connector
Publisher: NPC-Worldwide
Source code: github.com/NPC-Worldwide/npcpy
Est. context load: ~550 tokens / turn (~3 tool schemas, 0.27% of 200k context)
Popularity: 1.5k GitHub stars
Last updated: 2026-10-30
Last graded: 2026-10-22

Community

Discussions for Npcpy

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Npcpy helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude