CTFd MCP Server
Connect to CTFd instance, download tasks and submit flags
CTFd MCP Server
A lightweight and extensible Model Context Protocol (MCP) server for interacting with any CTFd instance. This project enables AI tools and automation to authenticate, retrieve challenges, and submit flags through MCP tools.
Overview
This project acts as a bridge between CTFd and AI-driven systems by providing a unified interface. It supports multiple authentication modes, dynamic base URL control, and direct MCP tool integration.
The server is validated using the official demo instance at https://demo.ctfd.io.
Features
- Dynamic BASE_URL configuration
- Token and cookie authentication
- Username/password login
- List challenges with optional filtering
- Submit flags programmatically
- Compatible with MCP-based AI tools (Claude, Codex, Amp, Gemini)
- Clean and extensible TypeScript codebase
Quickstart
Option 1: npx (no install)
npx ctfd-mcp-server
Option 2: Global install
pnpm install -g ctfd-mcp-server
ctfd-mcp-server
Option 3: From source
git clone https://github.com/tomek7667/ctfd-mcp-server.git
cd ctfd-mcp-server
pnpm install
pnpm run build
pnpm start
Tools
| Tool | Description |
|---|---|
set_base_url(url) | Set the base URL for the CTFd instance |
set_token(token) | Set authentication token |
set_cookie(cookie) | Set session cookie |
login(username, password) | Login with credentials |
challenges(category?) | List challenges, optionally filtered by category |
challenge(identifier) | Get challenge details by name or ID |
submit_flag(challenge_name?, challenge_id?, flag) | Submit a flag |
scoreboard() | Get the CTFd scoreboard |
progress() | Get current user's progress |
health() | Check connection health |
Client Setup
Claude Desktop
Claude Desktop supports MCP servers via a JSON configuration file.
Config file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Using npx (recommended):
{
"mcpServers": {
"ctfd": {
"command": "npx",
"args": ["-y", "ctfd-mcp-server"],
"env": {
"BASE_URL": "https://demo.ctfd.io",
"CTFD_TOKEN": "<your ctfd api token>"
}
}
}
}
Using global install:
{
"mcpServers": {
"ctfd": {
"command": "ctfd-mcp-server",
"env": {
"BASE_URL": "https://demo.ctfd.io",
"CTFD_TOKEN": "<your ctfd api token>"
}
}
}
}
Restart Claude Desktop after editing the config.
OpenAI Codex CLI
Codex CLI stores MCP configuration in ~/.codex/config.toml.
Using the CLI:
codex mcp add ctfd -- npx -y ctfd-mcp-server
Or edit ~/.codex/config.toml directly:
[mcp_servers.ctfd]
command = "npx"
args = ["-y", "ctfd-mcp-server"]
[mcp_servers.ctfd.env]
BASE_URL = "https://demo.ctfd.io"
CTFD_TOKEN = "<your ctfd api token>"
Use /mcp in the Codex TUI to verify the server is connected.
Amp
Amp supports MCP servers via the amp.mcpServers setting in VS Code settings.json.
Config file location (VS Code):
- macOS:
~/Library/Application Support/Code/User/settings.json - Windows:
%APPDATA%\Code\User\settings.json - Linux:
~/.config/Code/User/settings.json
Using npx (recommended):
{
"amp.mcpServers": {
"ctfd": {
"command": "npx",
"args": ["-y", "ctfd-mcp-server"],
"env": {
"BASE_URL": "https://demo.ctfd.io",
"CTFD_TOKEN": "<your ctfd api token>"
}
}
}
}
Via CLI:
amp mcp add ctfd npx -y ctfd-mcp-server
Gemini CLI
Gemini CLI stores MCP configuration in ~/.gemini/settings.json.
Using npx (recommended):
{
"mcpServers": {
"ctfd": {
"command": "npx",
"args": ["-y", "ctfd-mcp-server"],
"env": {
"BASE_URL": "https://demo.ctfd.io",
"CTFD_TOKEN": "<your ctfd api token>"
}
}
}
}
Via CLI:
gemini mcp add ctfd npx -- -y ctfd-mcp-server
Use /mcp in Gemini CLI to verify server status.
Docker
docker build -t ctfd-mcp-server .
docker run -i ctfd-mcp-server
For clients that support Docker-based MCP servers:
{
"mcpServers": {
"ctfd": {
"command": "docker",
"args": ["run", "-i", "--rm", "ctfd-mcp-server"]
}
}
}
Compatibility
| Feature | Supported |
|---|---|
| Transport | stdio |
| Node.js | >=18.0.0 |
| Platforms | macOS, Linux, Windows |
Tested Clients
| Client | Status |
|---|---|
| Claude Desktop | ✅ Verified |
| OpenAI Codex CLI | ✅ Verified |
| Amp | ✅ Verified |
| Gemini CLI | ✅ Verified |
Environment Variables
| Variable | Description | Default |
|---|---|---|
BASE_URL | CTFd instance base URL | https://demo.ctfd.io |
Development
# Clone and install
git clone https://github.com/tomek7667/ctfd-mcp-server.git
cd ctfd-mcp-server
pnpm install
# Build
pnpm run build
# Run
pnpm start
# Watch mode (auto-rebuild)
pnpm run watch
Support
For support, email [email protected] or open an issue through the GitHub repository. Community contributions and improvements are always welcome.
License
Server Terkait
Medialister
Gateway to editorial ads
Thoughtbox
next-generation MCP reasoning tool. successor to Waldzell AI's Clear Thought.
OctoEverywhere For 3D Printing
A 3D Printing MCP server that allows for querying for live state, webcam snapshots, and 3D printer control.
FHIR MCP Server
FHIR MCP Server – helping you expose any FHIR Server or API as a MCP Server.
KSeF
MCP server for Poland's national e-invoicing system KSeF (Krajowy System e-Faktur). Provides 12 tools for complete KSeF API integration including session management, invoice querying/submission, export generation, and system monitoring. Built with Rust for reliability and performance. Perfect for Polish businesses automating e-invoicing processes and developers building KSeF compliance tools.
Cycling Coach AI
AI-powered cycling training coach: personalized training plans, daily workouts, nutrition, strength training, fitness metrics (FTP, VO2Max), and Strava, Garmin, Wahoo, MyWhoosh, and Rouvy integrations.
Minecraft MCP Integration
Enables AI assistants to interact with a Minecraft server using the Model Context Protocol (MCP).
Sweet Home 3D MCP Server
MCP server plugin for Sweet Home 3D that lets AI assistants create walls, place furniture, apply textures, and render 3D interior designs — 42 tools, zero external dependencies.
Zcash MCP
MCP server for Zcash with 22 tools for shielded transactions, attestation verification, and wallet management
Vigil
System Scanner for Vulnerabilities