Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Lab of deliberately vulnerable MCP servers v1.0.0

Use this resource to learn pentesting and AI agent red teaming in an isolated lab

New

  • 412 downloads
  • 169 likes
  • 159 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install vulnerable-mcp-security-lab

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent guides you through installing deliberately vulnerable MCP servers covering indirect prompt injection, path traversal, code execution and typosquatting. These servers are for training and must stay on isolated machines.

Mostly picked by

Updated November 2, 2026

Card for the “Lab of deliberately vulnerable MCP servers” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: prerequisites and lab installation
  • SKILL.md: description of the six vulnerable servers
  • SKILL.md: warnings about use in an isolated environment

Good fit for

  • You train a security team on the risks of AI agents
  • You are preparing a red teaming exercise on MCP tools

Not for

    Tags

    • security
    • red teaming
    • prompt injection
    • training

    About

    You say

    “Start the indirect prompt injection server and show me how to detect it.”

    Card for the “Lab of deliberately vulnerable MCP servers” skill

    Skill published by reason-machines under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to learn pentesting and AI agent red teaming in an isolated lab
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE0 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md11.7 KB

    Origin and licence

    Listed unmodified

    Author
    reason-machines
    Source
    github.com/reason-machines/mcp-skills/tree/8b5d6f4b8c9ec7285afe142d0f424d595a74c472/skills/vulnerable-mcp-servers-lab
    Licence
    MIT

    Notice

    « vulnerable-mcp-servers-lab » (reason-machines, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.