MCP App Store
by KeenEthics
ShieldPi icon

ShieldPi MCP Server for Claude

By ShieldPi

Overview

ShieldPi's connector answers AI security questions from ShieldMap, ShieldPi's public map of AI security data, without leaving the conversation. It needs no account and every tool is read-only. - Check a package: give an npm, PyPI, Go, Maven, crates.io, NuGet, RubyGems, Packagist or Swift package name (and optionally a version) and get its published vulnerabilities and malicious-package reports, which versions are affected, and the release to upgrade to. Where no release fixes an advisory yet, it adds the advisory's own workaround and ShieldPi's general guidance, labelled apart. - Search: find agent frameworks, MCP servers, MCP SDKs and coding agents on ShieldMap by name, the most advisories first. - Read an advisory: look up a GHSA or CVE ID for what it is, the affected packages and versions, and the fix. - Requirements: quote what the EU AI Act, NIST AI 600-1 and the AI RMF, the CoSAI Risk Map and the OWASP Top 10 for LLM Applications 2026 crosswalk say on an article, risk, control or topic, with links to the source. These are quotes for navigation, not legal advice. - Methodology: describe ShieldPi's scan modes, coverage figures and how findings are verified. ShieldMap is built from the GitHub Advisory Database, OSV, CISA KEV, MITRE ATLAS, the OWASP GenAI Security Project, the EU AI Act consolidated text on EUR-Lex, NIST and CoSAI, and refreshed daily. Each answer names its source and licence.

How to connect

  1. Claude: Open the ShieldPi listing in the Claude connectors directory and choose Connect. Claude listing ShieldPi exposes 7 tools here.

Tools

platform_stats

Claude
Describe this ShieldPi deployment: its attack corpus version, how many scan modes it supports, how scan results are judged, what its standards mappings do and do not establish, and the MCP protocol versions and authorization model of this server.

scan_modes

Claude
List the scan modes this ShieldPi deployment supports and the kind of target each one tests.

shieldmap_advisory

Claude
Look up one advisory on ShieldMap by its GHSA or CVE ID: its summary and severity, the affected packages and version ranges, the fixed versions, whether CISA lists it as exploited in the wild, and the original advisory's link. Where no release fixes it, mitigations carries its own workaround text and ShieldPi's general guidance, labelled apart as in shieldmap_check_package. An ID ShieldMap does not have returns advisory null.

shieldmap_check_package

Claude
Check one package against ShieldMap's vulnerability and malicious-package advisories. Use it to find out whether a dependency, or one installed version of it, has published advisories. With a version, only the advisories that version is affected by are returned, with the release to upgrade to. For advisories no release fixes, mitigations lists the advisory's own workaround text (source "advisory", attributed) and ShieldPi's general guidance for the kind of weakness (source "shieldpi", not a vendor fix). A package ShieldMap does not track returns on_shieldmap false: ShieldMap has no data on it, which does not mean it is safe.

shieldmap_requirements

Claude
Quote what the EU AI Act, NIST AI 600-1, the NIST AI RMF, the CoSAI Risk Map and the OWASP Top 10 for LLM Applications 2026 crosswalk say about an id or a topic, with links to ShieldMap and the source and the licence of each result. EU AI Act text comes from its current consolidated version; a query about its dates, or about Article 113, also returns the application dates. The results are quotations to navigate by, not legal advice.

verification_methodology

Claude
Explain how ShieldPi verifies findings and where each method stops: model scans (a judge jury and a StrongREJECT score threshold) and the public MCP server probe (static metadata only, no tool execution), with a link to the published methodology.

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/shieldpi"><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/shieldpi)