Is "@pandysp/claude-code-mcp" on MCP Registry Safe to Install?

GitHub Actions · mcp · v2.2.0

MCP server that runs Claude Code as a tool with session continuity

Risk Assessment

Analyzed
100
out of 100
CRITICAL

112 security findings detected across all analyzers

MCP server analyzed for tool poisoning, prompt injection, and data exfiltration

Severity Breakdown

2
Critical
68
High
36
Medium
0
Low
0
Info

Finding Categories

48
Malware Signatures
17
Secrets
33
IoC Indicators

YARA Rules Matched

8 rules(48 hits)
postinstall obfuscation postinstall network communication postinstall system command postinstall environment access postinstall persistence mechanism postinstall file manipulation credential env files 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.

About This Extension

MCP server that runs Claude Code as a tool with session continuity

Detailed Findings

79 total

YARA Rule Matches

8 rules

Indicators of Compromise

Network indicators, suspicious strings, and potential IoCs extracted during analysis

URLs
12
IP Addresses
3
Domains
21
Strings
33

All Indicators · 33

Domain
detected Domain: main.java

XIOC detected Domain: main.java

extracted_from_files

Domain
detected Domain: www.npmjs.com

XIOC detected Domain: www.npmjs.com

extracted_from_files

URL
detected URL: https://img.shields.io/npm/v/@pandysp/claude-code-mcp)](https://www.npmjs.com/package/@pandysp/claude-code-mcp)

XIOC detected URL: https://img.shields.io/npm/v/@pandysp/claude-code-mcp)](https://www.npmjs.com/package/@pandysp/claude-code-mcp)

extracted_from_files

URL
detected URL: https://github.com/pandysp/claude-code-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/pandysp/claude-code-mcp/actions/workflows/ci.yml)

XIOC detected URL: https://github.com/pandysp/claude-code-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/pandysp/claude-code-mcp/actions/workflows/ci.yml)

extracted_from_files

URL
detected URL: https://modelcontextprotocol.io/):

XIOC detected URL: https://modelcontextprotocol.io/):

extracted_from_files

URL
detected URL: https://docs.anthropic.com/en/docs/claude-code)

XIOC detected URL: https://docs.anthropic.com/en/docs/claude-code)

extracted_from_files

URL
detected URL: https://developer.mozilla.org

XIOC detected URL: https://developer.mozilla.org

extracted_from_files

IP
detected Domain: script.py

XIOC detected Domain: script.py

extracted_from_files

URL
detected URL: https://semver.org/spec/v2.0.0.html).

XIOC detected URL: https://semver.org/spec/v2.0.0.html).

extracted_from_files

Domain
detected Domain: args.params.name

XIOC detected Domain: args.params.name

extracted_from_files

Domain
detected Domain: start.sh

XIOC detected Domain: start.sh

extracted_from_files

Domain
detected Domain: changelog.md

XIOC detected Domain: changelog.md

extracted_from_files

URL
detected URL: https://keepachangelog.com/en/1.0.0/),

XIOC detected URL: https://keepachangelog.com/en/1.0.0/),

extracted_from_files

Domain
detected Domain: expect.fail

XIOC detected Domain: expect.fail

extracted_from_files

Domain
detected Domain: eventemitter.call

XIOC detected Domain: eventemitter.call

extracted_from_files

Domain
detected Domain: server.run

XIOC detected Domain: server.run

extracted_from_files

Domain
detected Domain: result.tools

XIOC detected Domain: result.tools

extracted_from_files

Domain
detected Domain: response.id

XIOC detected Domain: response.id

extracted_from_files

Domain
detected Domain: parsed.is

XIOC detected Domain: parsed.is

extracted_from_files

Domain
detected Domain: main.py

XIOC detected Domain: main.py

extracted_from_files

Domain
detected Domain: semver.org

XIOC detected Domain: semver.org

extracted_from_files

Domain
detected Domain: github.com

XIOC detected Domain: github.com

extracted_from_files

Domain
detected Domain: img.shields.io

XIOC detected Domain: img.shields.io

extracted_from_files

Domain
detected Domain: modelcontextprotocol.io

XIOC detected Domain: modelcontextprotocol.io

extracted_from_files

Domain
detected Domain: docs.anthropic.com

XIOC detected Domain: docs.anthropic.com

extracted_from_files

URL
detected URL: https://github.com/steipete/claude-code-mcp).

XIOC detected URL: https://github.com/steipete/claude-code-mcp).

extracted_from_files

Domain
detected Domain: readme.md

XIOC detected Domain: readme.md

extracted_from_files

URL
detected URL: https://github.com/pandysp/claude-code-mcp#readme

XIOC detected URL: https://github.com/pandysp/claude-code-mcp#readme

extracted_from_files

URL
detected URL: https://github.com/pandysp/claude-code-mcp/issues

XIOC detected URL: https://github.com/pandysp/claude-code-mcp/issues

extracted_from_files

URL
detected URL: https://github.com/pandysp/claude-code-mcp.git

XIOC detected URL: https://github.com/pandysp/claude-code-mcp.git

extracted_from_files

URL
detected URL: https://github.com/steipete

XIOC detected URL: https://github.com/steipete

extracted_from_files

Domain
detected Domain: keepachangelog.com

XIOC detected Domain: keepachangelog.com

extracted_from_files

Domain
detected Domain: developer.mozilla.org

XIOC detected Domain: developer.mozilla.org

extracted_from_files

Security Analysis Summary

Security Analysis Overview

@pandysp/claude-code-mcp is a mcp extension published by GitHub Actions. Version 2.2.0 has been analyzed by the Risky Plugins security platform, receiving a risk score of 100/100 (CRITICAL risk) based on 112 security findings.

Risk Assessment

This extension presents critical security risk. Severe issues were detected, potentially including malware indicators, exposed secrets, or dangerous behaviors. Installation is strongly discouraged until these issues are addressed.

Findings Breakdown

  • Critical: 2 finding(s)
  • High: 68 finding(s)
  • Medium: 36 finding(s)

What Was Analyzed

The security assessment covers multiple analysis categories:

  • Malware Detection: YARA rule matching against 2,400+ malware signatures
  • Secret Detection: Scanning for exposed API keys, tokens, and credentials
  • Static Analysis: Code-level security analysis for common vulnerability patterns
  • Network Analysis: Detection of suspicious network communications and endpoints
  • Obfuscation Detection: Identification of code obfuscation techniques

Developer Information

@pandysp/claude-code-mcp is published by GitHub Actions on the mcp marketplace.

Recommendation

This extension is not recommended for installation without thorough manual review. Consider alternatives with lower risk scores, or contact the developer to address the identified security concerns.

Frequently Asked Questions