MCP Registry

mcp-oauth-provider

6529c480-6364-556a-8dfd-b54c48a4e56b | Store v1.0.0
100/ 100
CRITICAL risk
Risk verdict
Do not install

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

Analysis record

Analysed
2 months ago 26 August 2026
Version
v1.0.0
Artifact
SHA256 0a089eeb…058dd5
Detail
Full list

Evidence ledger

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

96 findings
Showing 25 of 44 · highest severity first

YARA Rule Matches

7 rules
SeverityRuleHitsFilesMetadata
LOWpostinstall file download 13
src/server/callback.tsREADME.mddist/__tests__/oauth-flow.test.js.map +10 more
-
LOWpostinstall environment access 10
src/client/storage.tssrc/server/callback.tsdist/client/storage.js +7 more
-
LOWpostinstall file manipulation 13
dist/client/storage.jsdist/__tests__/storage.test.jssrc/__tests__/storage.test.ts +10 more
-
LOWpostinstall crypto operations 3
dist/client/config.js.mapdist/client/config.jssrc/client/config.ts
-
LOWpostinstall obfuscation 4
src/server/callback.tsdist/server/callback.jsREADME.md +1 more
-
LOWpostinstall network communication 1
README.md
-
LOWpostinstall system command 8
dist/client/index.js.mapsrc/server/templates.tsdist/client/storage.js.map +5 more
-

Finding Categories

16
Secrets
28
Network

YARA Rules Matched

7 rules(52 hits)
postinstall file download postinstall environment access postinstall file manipulation postinstall crypto operations postinstall obfuscation postinstall network communication postinstall system command

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 unknown malware; evidence quality weak.

This package presents a critical automated risk profile, but the absence of detailed finding descriptions in the evidence bundle prevents a conclusive automated assessment. The scanner reports 52 malware-signature hits and 28 network findings, which are significant anomalies for an MCP OAuth provider. However, without the specific file paths, matched YARA rule names, or target domains, it is impossible to distinguish between a compromised dependency and false positives from bundled minified code. Legitimate OAuth providers should not trigger high-severity malware signatures. Security Recommendation: Do not install this package in a sensitive environment until a manual analyst reviews the specific YARA matches and network destinations to confirm whether this is a supply chain attack or a scanner false positive.

Key Reasons

  • Critical risk score (100) derived from 52 high/critical malware signatures
  • 28 network findings detected in an OAuth utility package
  • Zero user base suggests unpublished or test package
  • Missing 'top_findings' data blocks manual verification

False Positive Considerations

  • Malware signatures commonly trigger on minified JavaScript in dist/ bundles
  • Network findings may be legitimate HTTP client functionality (package purpose)
  • Risk score inflation from automated heuristics vs confirmed threats

Reviewed 2026-04-12; recommended action: reanalyze; model confidence 65%.

Source Code Viewer

Source Code Not Available

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

About This Extension

MCP OAuth client provider for streamable HTTP clients

Frequently Asked Questions