Participant MCP
Enables CTF players to list challenges, retrieve challenge details, view the scoreboard, and submit flags.
README
KernelKittens CTF Event Kit
This repository starts from CTFd 3.8.7 and adds three public components:
- A transactional solve outbox for CTFd.
- A Rust event ledger service.
- A participant-only MCP service exposing
ctf_list_challenges,ctf_get_challenge,ctf_get_scoreboard, andctf_submit_flag.
Staff and administrative operations are outside the participant MCP. The original CTFd README follows.
What is CTFd?
CTFd is a Capture The Flag framework focusing on ease of use and customizability. It comes with everything you need to run a CTF and it's easy to customize with plugins and themes.

Features
- Create your own challenges, categories, hints, and flags from the Admin Interface
- Dynamic Scoring Challenges
- Unlockable challenge support
- Challenge plugin architecture to create your own custom challenges
- Static & Regex based flags
- Custom flag plugins
- Unlockable hints
- File uploads to the server or an Amazon S3-compatible backend
- Limit challenge attempts & hide challenges
- Automatic bruteforce protection
- Individual and Team based competitions
- Have users play on their own or form teams to play together
- Scoreboard with automatic tie resolution
- Hide Scores from the public
- Freeze Scores at a specific time
- Scoregraphs comparing the top 10 teams and team progress graphs
- Markdown content management system
- SMTP + Mailgun email support
- Email confirmation support
- Forgot password support
- Automatic competition starting and ending
- Team management, hiding, and banning
- Customize everything using the plugin and theme interfaces
- Importing and Exporting of CTF data for archival
- And a lot more...
Install
- Install dependencies:
pip install -r requirements.txt- You can also use the
prepare.shscript to install system dependencies using apt.
- You can also use the
- Modify CTFd/config.ini to your liking.
- Use
python serve.pyorflask runin a terminal to drop into debug mode.
You can use the auto-generated Docker images with the following command:
docker run -p 8000:8000 -it ctfd/ctfd
Or you can use Docker Compose with the following command from the source repository:
docker compose up
Check out the CTFd docs for deployment options and the Getting Started guide
Live Demo
https://demo.ctfd.io/
Support
To get basic support, you can join the MajorLeagueCyber Community:
If you prefer commercial support or have a special project, feel free to contact us.
Managed Hosting
Looking to use CTFd but don't want to deal with managing infrastructure? Check out the CTFd website for managed CTFd deployments.
MajorLeagueCyber
CTFd is heavily integrated with MajorLeagueCyber. MajorLeagueCyber (MLC) is a CTF stats tracker that provides event scheduling, team tracking, and single sign on for events.
By registering your CTF event with MajorLeagueCyber users can automatically login, track their individual and team scores, submit writeups, and get notifications of important events.
To integrate with MajorLeagueCyber, simply register an account, create an event, and install the client ID and client secret in the relevant portion in CTFd/config.py or in the admin panel:
OAUTH_CLIENT_ID = None
OAUTH_CLIENT_SECRET = None
Credits
- Logo by Laura Barbera
- Theme by Christopher Thompson
- Notification Sound by Terrence Martin
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
