MCP App Store
by KeenEthics
VisionEdge AIScan icon

VisionEdge AIScan MCP Server for ChatGPT

By VisionEdge, s. r. o.

Overview

AIScan checks software written with AI coding tools for the security mistakes those tools often make. What you can ask: - Is a package safe to install? AIScan catches packages that do not exist (AI hallucinations that attackers register with malware, known as slopsquatting), known malicious packages, brand new look-alike packages, typosquats and known vulnerabilities from OSV and GitHub advisories, with the CISA known exploited flag and EPSS exploit probability. - Check a whole package.json, requirements.txt, pyproject.toml or lockfile and get the exact upgrades. - Scan code you share or that your AI assistant wrote: API keys in code or exposed to the browser (always reported redacted), model output reaching eval, a shell, SQL or HTML, user input inside system prompts, public LLM endpoints without login or rate limits, Supabase tables without Row Level Security, open Firebase rules, risky MCP servers and agent permissions, and hidden Unicode instructions in rules files. - Scan a public GitHub repository end to end. - Run a passive check of a website you own: HTTPS, security headers, keys inside the JavaScript sent to visitors, public source maps, Supabase and Firebase setup. - See the newest vulnerabilities in AI frameworks, LLM SDKs, vector databases and MCP tooling. Every finding has a severity, a plain language explanation, the location, a concrete fix and its mapping to the OWASP Top 10 for LLM Applications, the OWASP Top 10 for Agentic Applications and CWE. Code is processed only to answer the request and is not stored. Limits: AIScan is an automated scanner and cannot prove that software is secure. Website checks are passive and need the user to confirm they own the site or may test it. Deep website checks and live monitoring are available on the AIScan website.

How to connect

  1. ChatGPT: Open the VisionEdge AIScan listing in the ChatGPT app directory and choose Connect. ChatGPT listing VisionEdge AIScan exposes 6 tools here.

Tools

check_dependencies

ChatGPT
Check the content of a dependency manifest or lockfile (requirements.txt, pyproject.toml, Pipfile, poetry.lock, uv.lock, package.json, package-lock.json, yarn.lock, pnpm-lock.yaml) for hallucinated, malicious, typosquatted, deprecated and vulnerable packages. Returns a grade and concrete upgrades.

check_package

ChatGPT
Check whether an npm or PyPI package is safe to install. Detects packages that do not exist (AI hallucinations that attackers register: slopsquatting), known malware, suspicious brand new look-alike packages, typosquats and known vulnerabilities (OSV, GitHub advisories, CISA KEV, EPSS). Use it before installing any dependency an AI tool suggested.

get_ai_threat_feed

ChatGPT
Newest published vulnerabilities in AI frameworks, LLM SDKs, vector databases, agent and MCP tooling (OSV and GitHub advisories, with CISA known exploited flag and EPSS exploit probability). Optionally filter by ecosystem, minimum severity or package name.

scan_code

ChatGPT
Security scan of source files the user shared or you generated: hardcoded or browser-exposed API keys (reported redacted), LLM output reaching eval, shell, SQL or HTML, prompt injection risks, unauthenticated LLM endpoints, Supabase tables without Row Level Security, open Firebase rules, risky MCP and agent settings, hidden Unicode instructions, and the packages the code imports. Nothing is stored.

scan_github_repo

ChatGPT
Download a public GitHub repository and run the full AIScan code scan on it (dependencies and package hallucination, secrets, AI code risks, Supabase and Firebase configuration, agents and MCP, hidden instructions). The code is deleted right after the scan.

scan_website

ChatGPT
Passive security check of a website the user owns or is allowed to test: HTTPS and certificate, security headers, cookies, API keys inside the JavaScript sent to visitors, public source maps, Supabase and Firebase setup, AI endpoints. It only loads what a normal browser loads. Ask the user to confirm ownership or permission first and pass confirm_authorized true.

Capabilities

Detect Hallucinated, Malicious And Typosquatted Npm And Pypi Packages Before InstallationFind Known Vulnerabilities In Dependencies With Osv, Github Advisories, Cisa Kev And EpssFind Hardcoded And Browser Exposed Api Keys, Always Reported RedactedFind Unsafe Handling Of Llm Output: Eval, Shell, Sql, Html RenderingCheck Supabase Row Level Security And Firebase RulesReview Mcp Server And Ai Agent Configurations For Excessive PermissionsDetect Hidden Unicode Instructions In Agent Rules FilesPassive Security Check Of A Website The User OwnsNewest Vulnerabilities In Ai Frameworks And Mcp Tooling

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/visionedge-aiscan"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/visionedge-aiscan)