AI Developer Tools
mcploitable
A collection of deliberately vulnerable MCP servers for training in agentic security, mapped to the OWASP Top 10 for Agentic Applications.
mcploitable
What is mcploitable?
mcploitable is an open-source project that provides deliberately vulnerable Model Context Protocol (MCP) servers for security training. Each server simulates a real-world vulnerability from the OWASP Top 10 for Agentic Applications, allowing users to practice identifying and exploiting agentic security flaws in a safe, containerized environment.
mcploitable vs Similar AI Tools
| Pricing Model | Free | Free | Free | Free |
| Free Credits | ||||
| Key Features |
|
|
|
|
| Pros |
|
|
|
|
| Cons |
|
|
|
|
| Best For |
|
|
|
|
How to use mcploitable?
- 1Clone the repository and ensure Docker is installed.
- 2Run 'docker compose build' to build the images.
- 3Use 'docker compose run --rm -T <service>' to start a vulnerable server (e.g., mail, calc).
- 4Register the server in an MCP client (e.g., Claude Code) using the provided configuration.
- 5Use the interactive ./play script to explore vulnerabilities and submit exploits in a CTF-style lab.
mcploitable Key Features
- Seven breakable boxes covering OWASP Agentic Top-10 vulnerabilities
- Three guided simulations for cascading failures, human-agent trust, and rogue agents
- Network-isolated Docker containers for safe execution
- No self-awareness or hints in servers; vulnerabilities are latent
- CTF lab layer with level ladder (L0-L3) for each scenario
- Comprehensive documentation and test suite
mcploitable Use Cases
- Agentic security training for development teams
- CTF competitions and capture-the-flag events
- Research and analysis of OWASP Top 10 for Agentic Applications
- Hands-on learning for AI agent developers and security professionals
mcploitable Pricing & Free Credits
mcploitable currently operates on a Free model.
This tool is completely free to use
mcploitable Pros & Cons
Pros
- Covers full OWASP Agentic Top-10 in a realistic manner
- Docker isolation prevents accidental damage
- CTF lab provides structured learning with difficulty levels
- Well-documented with results and simulation notes
Cons
- Requires Docker and technical setup
- Not for production use; only for lab environments
- Steep learning curve for beginners without security background
What is mcploitable best for?
- Security researchers focusing on AI agent vulnerabilities
- Developers building MCP-based applications
- CTF organizers and participants
- Educators teaching agentic security