It provides a reproducible sandbox for testing context injection risks, filling a critical gap in AI agent security testing.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“Run them only inside the bundled, network-isolated Docker containers.”— readme
“ordinary-looking [MCP](https://modelcontextprotocol.io) servers”— readme
FAQ
What is Mcploitable?
Mcploitable is an experimental security tool that simulates vulnerabilities in the Model Context Protocol to help AI developers test and teach how agents can be tricked by context injection attacks.
What does Mcploitable do?
To test whether my AI agent can be deceived by context injection attacks in a safe, controlled environment.
Why does Mcploitable matter?
It provides a reproducible sandbox for testing context injection risks, filling a critical gap in AI agent security testing.
How much does Mcploitable cost?
Free
Is Mcploitable free?
Yes — Mcploitable has a free tier. Pricing as stated on its own page: Free
Is Mcploitable open source?
Yes — Mcploitable is open source.
Can I self-host Mcploitable?
Yes — Mcploitable can be self-hosted.
What does Mcploitable integrate with?
mcp
How popular is Mcploitable?
As tracked by KanonAgent: 2 upvotes (first indexed 2026-08-21).
What are the best Mcploitable alternatives?
Similar AI agents tracked by KanonAgent: deepseek-harness, open-design, deer-flow, Agent-Reach, ruflo, oh-my-openagent.