MCP Registry

@agent-infra/mcp-client

af003672-8bf5-5788-b7ae-e7447448ed66 | Store v1.2.29
44/ 100
MEDIUM risk
Risk verdict
Review before use

Score-based assessment (medium risk, 44/100). An AI review is available in the AI review tab.

No individual score drivers were recorded for this analysis.

Analysis record

Analysed
7 months ago 19 April 2026
Version
v1.2.29
Artifact
SHA256 6712a2b0…c77a25
Detail
Full list

Evidence ledger

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

20 findings

YARA Rule Matches

5 rules
SeverityRuleHitsFilesMetadata
HIGHpostinstall network communication

Network communication detected

2
dist/index.mjsdist/index.js
Risky Plugins Authors FP 30%
HIGHpostinstall file manipulation

File system manipulation detected

4
README.mddist/index.d.tsdist/index.mjs +1 more
Risky Plugins Authors FP 20%
HIGHpostinstall system command

System command execution detected

5
README.mddist/index.mjsdist/index.js +2 more
Risky Plugins Authors FP 10%
HIGHpostinstall file download

File download activity detected

3
README.mddist/index.mjsdist/index.js
Risky Plugins Authors FP 30%
HIGHcredential env files

Environment configuration file path detected

2
dist/index.mjsdist/index.js
Risky Plugins Authors FP 10%

Finding Categories

16
Malware Signatures
1
Network

YARA Rules Matched

5 rules(16 hits)
postinstall network communication postinstall file manipulation postinstall system command postinstall file download credential env files

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 pup; evidence quality weak.

This package presents a high risk score driven entirely by 16 malware-signature matches and 1 network finding. However, automated heuristic scanners frequently misclassify legitimate code—particularly in complex environments like Electron or tooling infrastructure—as malware due to code structure similarities or fingerprinting collisions. The absence of tool-poisoning findings indicates the package does not attempt to manipulate the AI agent through hidden directives. While the low user count (0) suggests this is an unproven library, there is no direct evidence of credential harvesting or exfiltration. The high risk score likely reflects 'score inflation' from aggressive YARA rules rather than an active threat.

Key Reasons

  • High risk score (83.47) driven entirely by generic malware-signature matches which are high false-positive candidates
  • Zero tool-poisoning findings detected despite the package's nature as an MCP client
  • Zero credential-access or secret findings, indicating no immediate data theft patterns
  • Low user count (0) suggests unproven software but does not confirm malicious intent

False Positive Considerations

  • YARA malware-signature rules (16 findings) frequently trigger on legitimate code patterns or library bundles
  • Score inflation where generic signature matches disproportionately inflate the risk_score

Reviewed 2026-04-13; 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

An MCP Client to run servers for Electron apps, support same-process approaching

Frequently Asked Questions