MCP Registry

cas-parser-node-mcp

52f438c3-5902-5045-9131-9f07b1cd288b | Store v1.17.1
100/ 100
CRITICAL risk
No change since v1.17.0
AI review verdict
Do not install

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

Analysis record

Analysed
2 months ago 15 September 2026
Version
v1.17.1
Artifact
SHA256 61e569cd…597702
Detail
Full list

Evidence ledger

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

221 findings
Showing 25 of 37 · highest severity first

YARA Rule Matches

11 rules
SeverityRuleHitsFilesMetadata
LOWcredential env files 15
local-docs-search.jssrc/local-docs-search.tsoptions.mjs +12 more
-
LOWUsingCommandLineArguments 1
src/options.ts
-
LOWpostinstall file download 32
http.d.ts.mapcode-tool-worker.mjssrc/code-tool.ts +29 more
-
LOWNoUseEval 3
src/code-tool-worker.tscode-tool-worker.mjscode-tool-worker.js
-
LOWpostinstall network communication 27
src/code-tool-worker.tslocal-docs-search.jsmethods.mjs +24 more
-
LOWpostinstall system command 32
code-tool.jslocal-docs-search.jssrc/code-tool-worker.ts +29 more
-
LOWpostinstall environment access 15
instructions.d.tsoptions.d.tscode-tool-paths.d.cts +12 more
-
LOWpostinstall file manipulation 25
src/instructions.tscode-tool-worker.jscode-tool-worker.mjs +22 more
-
LOWpostinstall obfuscation 25
local-docs-search.jssrc/types.tssrc/code-tool-worker.ts +22 more
-
LOWpostinstall crypto operations 6
local-docs-search.jssrc/local-docs-search.tslocal-docs-search.mjs +3 more
-
LOWUsingShellInterpreterWhenExecutingOSCommands 3
src/code-tool.tscode-tool.jscode-tool.mjs
-

Finding Categories

15
Secrets
20
Network
110
IoC Indicators

YARA Rules Matched

11 rules(184 hits)
credential env files UsingCommandLineArguments postinstall file download NoUseEval postinstall network communication postinstall system command postinstall environment access postinstall file manipulation postinstall obfuscation postinstall crypto operations UsingShellInterpreterWhenExecutingOSCommands

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.

The 'CRITICAL' risk score of 100 is a statistical artifact caused by the analysis of a bundled JavaScript artifact (likely dist/index.js or similar). The evidence bundle shows 155 'high' severity findings, all attributed to 'malware-signature' and 'ioc' categories. In the context of modern Node.js applications, this is characteristic of dependency bundling: the server packages its dependencies (e.g., axios, node-fetch, etc.), triggering YARA rules and IoC extraction for every library included.

Crucially, this package shows zero findings in the defining threat categories for MCP servers: there are 0 'tool-poisoning' findings, 0 'secret' findings, and 0 'code-smell' findings related to environment variable harvesting. The absence of tool-poisoning findings indicates the package does not attempt to manipulate the AI agent through hidden directives in tool descriptions. While the scanner detected 8 'network' findings and 109 IoCs, these are consistent with standard web traffic (e.g., API calls to the Cas Parser API) and CDN references from bundled libraries, respectively. There is no signal of credential exfiltration (no targeted filesystem reads or secret harvesting).

This appears to be a benign package inflated by the scanner's sensitivity to bundled code rather than a malicious actor.

Key Reasons

  • Zero tool-poisoning findings detected (the primary MCP threat vector)
  • No secret or credential-harvesting logic found
  • High finding count (155 high severity) attributed entirely to generic malware-signature rules and IoCs in bundled code
  • No evidence of exfiltration architecture (network calls are consistent with stated API purpose)

False Positive Considerations

  • Bundled dependencies triggering YARA malware signatures
  • IoC extractor flagging CDN/infra domains and hex strings from minified JS

Reviewed 2026-04-13; recommended action: suppress false positive; model confidence 72%.

MCP version history

Risk trend by version

10 analyzed versions. Each point is the latest successful scan for that version; failed zero-score scans are hidden. Dates: First seen by Risky Plugins.

Selected
100
Change since first
No change
Change from previous
No change
Versions:
First analyzed version
1.11.0
First seen Apr 20, 2026
Risk range
100 to 100
Across analyzed versions
Latest analyzed version
1.17.1
First seen Sep 15, 2026
Selected version
critical
Version
v1.17.1
First seen 2 months ago
Risk score
100
Findings
331
Change vs previous
No change

Pick any point on the chart, then open the Source tab to read that version's code.

Source Code Viewer

Source Code Not Available

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

About This Extension

The official MCP Server for the Cas Parser API

Frequently Asked Questions