Back to search
rta-mcp-ctf
MCP serverGitHub
Self-hosted mini CTF on attacking AI agents and MCP servers. Docker Compose, CTFd, ten simulated challenges.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/torjan0--rta-mcp-ctf)HTML
<a href="/listings/torjan0--rta-mcp-ctf"><img src="/api/listings/torjan0--rta-mcp-ctf/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 58 lines
- # MCP Agent CTF on your machine
- Play ten browser challenges about how AI agents handle untrusted tools, messages,
- forms and tasks. The Forensics challenges use local artifacts. In the Attack
- challenges you play an attacker against a simulated organization. All companies,
- accounts, secrets, mail, packages and tools are fictional and stay inside the lab.
- ## Start
- Install Docker Engine or Docker Desktop with Compose. Allow about 2 GB of free
- disk for the images and state. From this directory run:
- ```sh
- docker compose up --build
- ```
- Open the [scoreboard](http://127.0.0.1:8000) and register a player account with
- a password of at least eight characters. Use the same name or email and password
- to sign in at the [lab](http://127.0.0.1:8100). Submit flags on the scoreboard.
- Both services listen on your computer's loopback address. If Docker runs on a
- remote host, use a secure tunnel rather than exposing these ports to the internet.
- ## Pick an agent backend
- The stack chooses a backend each time it starts:
- 1. Set `ANTHROPIC_API_KEY` in your shell for Claude Haiku 4.5 through the Anthropic API.
- 2. Or set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` for an account with
- Bedrock access to Claude Haiku 4.5. `AWS_SESSION_TOKEN` is passed through for
- temporary credentials. Set `AWS_DEFAULT_REGION` if needed.
- 3. With neither, the lab uses a scripted stand-in. The hub clearly labels this
- practice mode. It is useful for exploring the interfaces, but its behavior
- does not predict a real model's response to an attack.
- For example:
- ```sh
- ANTHROPIC_API_KEY=your_key docker compose up --build
- ```
- Each real model run costs a small amount. At the app's default accounting rates
- for Haiku 4.5, input is about $1 and output about $5 per million tokens; a
- short run is usually a fraction of a cent to a few cents. Your provider bills
- your own account. The lab also limits runs per player and total estimated spend.
- Provider prices can change, so check your provider before running many attempts.
- The A2 and A3 repositories are simulated in memory. Write issues directly on
- their lab pages. No GitHub account or token is needed.
- ## Reset
- `docker compose down` stops the stack and keeps accounts, scores and flags.
- To start a fresh game, run `docker compose down -v`, then `docker compose up --build`.
- The `-v` option permanently deletes this stack's accounts, scores and flags.
- All challenge effects are simulated. Do not put real credentials or personal
- information into the challenge forms.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.