MCP Registry

@iflow-mcp/mcp-ts-template

21f6c428-d755-5278-a680-37e66c7ae8c0 | Store v2.5.7
90/ 100
CRITICAL risk
AI review verdict
Do not install

The AI review rates the findings as likely false positive, but the risk score (90/100) still counts them.

Analysis record

Analysed
2 months ago 26 August 2026
Version
v2.5.7
Artifact
SHA256 29207b67…1e0b15
Detail
Full list

Evidence ledger

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

41 findings

YARA Rule Matches

20 rules
SeverityRuleHitsFilesMetadata
LOWcredential env files 2
README.mddist/index.js
-
LOWpostinstall persistence mechanism 3
README.mdpackage.jsondist/index.js
-
LOWpostinstall crypto operations 1
dist/index.js
-
LOWpostinstall file manipulation 2
README.mddist/index.js
-
LOWNoUseSocketManually 1
dist/index.js
-
LOWpostinstall registry modification 2
README.mddist/index.js
-
LOWpostinstall obfuscation 2
README.mddist/index.js
-
LOWpostinstall network communication 1
dist/index.js
-
LOWpostinstall system command 4
README.mdpackage.jsonLICENSE +1 more
-
LOWOriginsNotVerified 1
dist/index.js
-
LOWUsingShellInterpreterWhenExecutingOSCommands 1
dist/index.js
-
LOWCreatingCookiesWithoutTheSecureFlag 1
dist/index.js
-
LOWServerHostnameNotVerified 1
dist/index.js
-
LOWLocalStorageShouldNotBeUsed 1
dist/index.js
-
LOWDebuggerStatementsShouldNotBeUsed 1
dist/index.js
-
LOWUsingCommandLineArguments 1
dist/index.js
-
LOWNoUseEval 1
dist/index.js
-
LOWpostinstall file download 3
README.mdpackage.jsondist/index.js
-
LOWHavingAPermissiveCrossOriginResourceSharingPolicy 1
dist/index.js
-
LOWNoUseWeakRandom 1
dist/index.js
-

Finding Categories

6
Secrets

YARA Rules Matched

20 rules(31 hits)
credential env files postinstall persistence mechanism postinstall crypto operations postinstall file manipulation NoUseSocketManually postinstall registry modification postinstall obfuscation postinstall network communication postinstall system command OriginsNotVerified UsingShellInterpreterWhenExecutingOSCommands CreatingCookiesWithoutTheSecureFlag ServerHostnameNotVerified LocalStorageShouldNotBeUsed DebuggerStatementsShouldNotBeUsed UsingCommandLineArguments +4 more

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, @iflow-mcp/mcp-ts-template, is a boilerplate/starter kit for building Model Context Protocol servers using TypeScript. The CRITICAL risk score (100) and high volume of findings (1690) are statistical artifacts, not evidence of malicious behavior.

Why this is a False Positive:

  1. Massive IoC Count (1374): Template repositories typically bundle dependencies, lockfiles, or build artifacts to ensure the template works immediately. The scanner is detecting thousands of benign artifacts from minified JavaScript (e.g., webpack chunks), npm registry metadata, and standard Node.js module structures as "indicators of compromise".

  2. Malware Signature Matches (31): These signatures are triggering on generalized code patterns found in common libraries or build tools included in the template, not on a payload designed to harm the user.

  3. Tool Poisoning (1): As an SDK/framework template, it contains code to define or describe tools (e.g., description: "A tool that does X"). This is a standard definition, not a poisoning attack.

  4. Developer Profile: Published by chatflowdev with 0 users, this is infrastructure code, not a consumer-facing agent with hidden agendas.

Security Posture: Safe to use as a developer tool/template. The findings reflect the noise of scanning a codebase that includes other codebases.

Key Reasons

  • The package is explicitly a 'template' or 'starter kit', which always bundles high volumes of noise (dependencies, build artifacts) that scanners misinterpret as IoCs.
  • The number of findings (1690) is characteristic of bundled node_modules and minified files, not targeted malicious code.
  • 31 generic 'malware-signature' findings in a TypeScript template indicate the scanner is matching on code-smell patterns in build dependencies, not an actual payload.
  • A single tool-poisoning finding in a framework meant to define tools is almost certainly a tool definition (false positive).

False Positive Considerations

  • Bundled Node.js dependencies (minified JS)
  • IoC extractor misidentifying build artifacts/registry URLs
  • Generic malware signatures matching library code
  • Tool definitions in SDK code triggering poisoning rules

Reviewed 2026-04-12; recommended action: suppress false positive; model confidence 85%.

Source Code Viewer

Source Code Not Available

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

About This Extension

The definitive, production-grade template for building powerful and scalable Model Context Protocol (MCP) servers with TypeScript, featuring built-in observability (OpenTelemetry), declarative tooling, robust error handling, and a modular, DI-driven archi

Frequently Asked Questions