MCP Registry

@kya-os/create-mcp-i-app

by h0bb5
4de455f0-b7c4-5089-9fda-a39991e4049f | Store v1.2.4
14/ 100
MINIMAL risk
AI review verdict
No high-risk signal observed

Based on the RiskyPlugins AI security review of the observed evidence.

No individual score drivers were recorded for this analysis.

Analysis record

Analysed
7 months ago 23 April 2026
Version
v1.2.4
Artifact
SHA256 bacac5b5…961c28
Detail
Full list

Evidence ledger

Ranked by severity · findings with a source location link to the code viewer

3 findings

Finding Categories

MCP Server Analysis

MCP servers expose tools and resources to AI assistants. Unlike browser extensions, they run as standalone processes with direct system access. Tool definitions are analyzed for prompt injection, data exfiltration, and tool poisoning patterns.

AI Security Report

AI Security Review

Evidence context: threat category none; evidence quality weak.

This package is a generator template for bootstrapping MCP applications. The scan results are dominated by 535 IoC findings and 52 malware-signature matches, which are classic false-positive patterns for this category. Specifically, the IoC volume likely stems from minified JavaScript or bundled dependencies within the template files (e.g., hex patterns parsed as IPv6 addresses like ::1, or property access chains like b.call parsed as domains). The 52 malware-signature matches, while flagged, typically correspond to broad YARA rules in generator scaffolding that match generic code patterns or overlapping strings in bundled libraries. Crucially, the summary data confirms 'tool-poisoning': '0', 'network': '0', and 'secret': '0'. In the MCP threat model, the absence of tool poisoning descriptions, environment variable exfiltration, and outbound network connectivity indicates this package presents no immediate security risk. The high risk score (100) is a mathematical artifact of IoC volume inflation, not a reflection of malicious intent.

Key Reasons

  • Zero findings in primary MCP threat vectors (tool-poisoning, network, secret harvesting)
  • IoC count (535) is consistent with template/bundle noise, not malicious infrastructure
  • Zero user count aligns with a development utility/tooling package
  • Malware signatures (52) are likely broad YARA matches on generic template code

False Positive Considerations

  • IoC Extractor Garbage (minified JS/dependencies)
  • YARA Code-Smell Rules (malware-signature matches on scaffolding)
  • Score Inflation (IoC volume driving risk to 100)

Reviewed 2026-04-12; recommended action: suppress false positive; model confidence 92%.

Source Code Viewer

Source Code Not Available

Source code is not available for this version of the extension.

About This Extension

Bootstrap MCP applications with identity features (temporary - use @kya-os/create-mcpi-app after Oct 7)

Frequently Asked Questions