Agentic OWASP — MCP Security Review

    0

    Review Python and TypeScript MCP servers with a source scanner and a 12-control OWASP security checklist.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Agentic OWASP — MCP Security Review

    Example session with this skill installed

    Review this FastMCP server before release; triage scanner findings and review all 12 controls.

    • Read your context and instructions
    • Compiled the agentic owasp

    Confirmed findings with source locations and fixes; a 12-control evidence table with Pass, Fail, N/A, or Not scanned status; relevant MCP/ASI mappings.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The mcp-security skill from agentic-owasp-skills combines deterministic Semgrep scanning with a guided source review. It scopes an MCP server, triages findings against the code, works through 12 controls, and reports evidence, fixes, and mappings to the MCP Top 10 (2025) and Agentic Top 10 (2026). Includes the original skill, crosswalk, checklist, and Apache-2.0 license (packaged as LICENSE.txt). Install the scanner separately from upstream v0.2.0. Pre-release; OWASP mappings are the project's editorial judgment.

    Pre-release. Taint analysis stays within one function and recognizes documented handler idioms. Runtime, deployment, and client controls require manual evidence. Clean scans do not establish security.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    • Free with an Agensi account

    Requires

    GitHub
    Ghcr
    Access To Target Source Code MCP
    Agent with file reading and shell tools
    git
    uv (Python tool runner)
    Raw Html Return MCP
    Python

    Permissions

    Allowed Hosts

    github.com
    ghcr.io

    File Scopes

    Target
    MCP
    source
    config
    and
    docs

    Reads source and runs a local scanner. Optional setup downloads the upstream release or image. No skill credentials required.

    Listed4 days ago
    Updated2 days ago

    What's inside

    Frequently Asked Questions

    Review Python and TypeScript MCP servers with a source scanner and a 12-control OWASP security checklist.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use Agentic OWASP — MCP Security Review on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Security