MCP-Security-Review

    by Ifásola

    2

    Specialized static security scanner for MCP servers and Python tool handlers to prevent injection and data leaks.

    $5

    30-day refund guarantee

    Secure checkout via Stripe

    0 installsSecurity scanned

    Works with the AI tools you already use

    CClaude CodeCCursorCCodex CLIGGitHub CopilotGGemini CLIVVS CodeWWindsurf+15 more

    See it in action

    You say

    Run a security audit on my new sqlite-mcp-server to make sure there are no injection or path traversal vulnerabilities.

    Your agent does

    [HIGH] SQL Injection Found

    • File: server.py:42
    • Code: db.execute(f"SELECT * FROM logs WHERE id = {tool_input}")
    • Fix: Use parameterized queries: db.execute("SELECT * FROM logs WHERE id = ?", (tool_input,))

    [MED] Path Traversal Risk

    • File: files.py:12
    • Manual Check: Ensure base_path is sanitized.

    What you get

    Audit MCP servers before publishing to public registriesDetect command injection risks in AI tool handlersIdentify SSRF vulnerabilities in tools that fetch external URLsFind hardcoded secrets or sensitive data exposure in server logs

    About this skill

    What it does

    This skill provides a specialized security audit for Model Context Protocol (MCP) servers and Python-based tool servers. It performs a targeted static analysis focused specifically on the "input-to-sink" path—where AI-generated or user-controlled input meets dangerous system functions.

    Why use this skill

    AI tools are uniquely vulnerable because they often bridge the gap between natural language and local system execution. Standard scanners often miss the nuances of MCP tool handlers. This skill prioritizes findings in tool-definition files and identifies high-risk patterns like command injection, SSRF, and unsafe deserialization that could lead to full system compromise if an agent is manipulated.

    Supported checks

    • Injection: Command, Code, SQL, and Server-Side Template Injection.
    • Data Safety: Unsafe deserialization (pickle/yaml) and path traversal.
    • Network: SSRF via outbound HTTP calls to input-derived URLs.
    • Secrets: Scanning for hardcoded credentials or accidental logging of sensitive data.

    The output provides a prioritized list of vulnerabilities with exact file paths, line numbers, and actionable remediation steps, followed by a custom manual review checklist for the tool's architecture.

    security-audit
    mcp-server
    static-analysis
    python
    cybersecurity
    security
    appsec
    ai-tooling

    How to install

    Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 28 days ago

    Listed28 days ago

    Creator

    Ifásola

    Frequently Asked Questions

    Popular in Security & Compliance

    dependency-auditor

    Audit dependencies for security, licenses, and health while generating a phased, low-risk upgrade and migration plan.

    $5
    1

    Bounty Security Pattern Master Library — 399 Vulnerability Patterns

    A premium library of 399 vulnerability patterns and DeFi attack vectors for AI-driven bug hunting and security audits.

    $75
    125.0(1)

    cybersecurity-bridge for all agentic

    A high-performance wrapper to route security tasks directly to the Anthropic-Cybersecurity-Skills library.

    Free
    21

    skill-security-vendor-pack

    Audit AI agent skills for security risks, packaging errors, and marketplace readiness with professional reports.

    Free
    17