Skip to content

Add MCPGoat — a deliberately vulnerable Model Context Protocol (MCP) target #276

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
SabyasachiDhal wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Add MCPGoat — a deliberately vulnerable Model Context Protocol (MCP) target #276

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 33 additions & 0 deletions _data/collection.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2418,6 +2418,39 @@
"single-player"
]
},
{
"url": "https://github.com/SabyasachiDhal/MCPGoat",
"name": "MCPGoat",
"collection": [
"offline",
"container"
],
"categories": [
"ctf",
"single-player"
],
"technology": [
"TypeScript",
"Node.js",
"Docker"
Comment on lines +2433 to +2435

@kingthorin kingthorin Aug 17, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Seem like this should include: MCP, LLM, AI

@kingthorin kingthorin Aug 22, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Still outstanding

],
"references": [
{
"name": "download",
"url": "https://github.com/SabyasachiDhal/MCPGoat"
},
{
"name": "guide",
"url": "https://sabyasachidhal.github.io/MCPGoat/"
}
],
"author": "Sabyasachi Dhal",
"description": "A deliberately vulnerable Model Context Protocol (MCP) server for hands-on MCP penetration-testing practice. 26 challenges cover MCP-specific attacks (tool poisoning, tool shadowing, rug-pulls, indirect prompt injection, sampling abuse) alongside classic web bugs (RCE, SSRF, SQLi, path traversal). Each challenge ships at Easy, Moderate and Difficult levels plus a Secure reference, for 78 capture-the-flag flags, and includes a victim-agent harness that shows a real LLM agent being exploited.",
"notes": "Authorized training use only; intentionally contains RCE, SSRF, SQLi and secret leakage. Keep it bound to 127.0.0.1 or run inside the provided container; never expose it to a network you do not own. Runs over Streamable HTTP; attack with the bundled client, MCP Inspector, curl or Burp. Quick start: docker compose up --build.",
"badge": "SabyasachiDhal/MCPGoat",
"stars": 1,
"last_contributed": "2026-08-17T14:11:28Z"
},
{
"url": "https://docs.rapid7.com/metasploit/metasploitable-2-exploitability-guide/",
"name": "Metasploitable 2",
Expand Down