"Capture The Flag (CTF) cybersecurity competitions and challenges" matching MCP servers:

Enables AI agents to directly manipulate Jupyter Notebook cells and structure through a secure, well-defined API, overcoming Cursor's AI agent mode limitations.

Give your AI app any GitHub link and the job you want done. UGT gets the project running on your computer and hands you the result.

A simple server that acts as a Master Control Program (MCP) for unified interaction with OpenAI and Anthropic (Claude) AI models through a single API endpoint.

An MCP server that lets AI models run code in 31 languages, evaluate symbolic math and logic problems, and measure complexity—exposed as 48 tools for execution, session management, translation, optimization, and more.

An MCP tool that enables AI agents to debug ELF binaries, particularly for CTF pwn challenges.

A production-ready foundation template for building Model Context Protocol (MCP) servers with FastAPI, featuring modular tools, comprehensive testing, and OpenShift deployment configurations. Includes automated transformation scripts to create custom domain-specific MCP servers.

MCP server for interacting with Autodesk Maya sessions, enabling multi-session management, arbitrary Python execution, and streaming output capture.

Lets an AI application instantiate, connect to, drive, capture output from, and interrogate a real BBC Micro emulator.

Build/flash/debug any Telink embedded SDK via natural language. MCP server with 8 tools for build, serial capture, and firmware flashing via bdt.exe.

Enables interaction with ESP32/MicroPython boards via tools for flashing firmware, running REPL code, file management, and serial capture, with support for progress notifications, cancellation, and error handling.

Enables executing Bash commands, pipelines, and scripts across Windows, macOS, and Linux via MCP, with support for multiple runtimes, timeouts, working directories, and stream capture.

A Model Context Protocol server that enables Claude and other AI assistants to generate personalized, contextually-relevant coding challenges in JavaScript, TypeScript, HTML, and CSS.

A Model Context Protocol server that enables AI assistants to interact with the Godot game engine, allowing them to launch the editor, run projects, capture debug output, and control project execution.

Connects AI assistants to live Roblox executor clients, letting the model run Luau in-game, walk the instance tree, decompile scripts, capture remote calls, and orchestrate work across multiple clients through 289 tools, a browser dashboard, and an in-game scripting surface. It also supports persistent playbooks, session traces, and verified agent workflows for repeatable automation.

Enables AI agents to launch the Godot editor, run and stop projects, capture debug output, inspect project details, and manage scenes and nodes through the Model Context Protocol.

A CTF Pwn AI-assisted debugging platform based on MCP, enabling AI to directly interact with remote GDB and CTF services for automated heap exploitation.

Enables AI coding assistants to connect to 2021 Roblox Studio / Aisaka Studio to capture screenshots, execute Luau, inspect and modify the DataModel, read/write scripts, and retrieve output logs via MCP.

A remote MCP server that enables AI agents to host HTML pages, generate PDFs, capture screenshots, scrape sites, and run sandboxed code using a CustomJS API key.

Enables agents and MCP clients to safely execute and verify multi-language code in a deterministic sandbox, using AST security analysis to block dangerous system calls and capture isolated execution telemetry.

Enables AI agents to read, edit, execute cells, and capture outputs from Jupyter notebooks directly within VS Code or Cursor via the Model Context Protocol.

An embedded MCP server for Cocos Creator that enables AI assistants to inspect and operate running Cocos projects through tools like execute_javascript, get_project_info, and screenshot capture.

Enables AI agents to safely execute Python code and shell commands in an ephemeral, isolated scratchpad with pre-execution AST security checks, timeout enforcement, token-shielded output, and file diff tracking. It also exposes static code-security inspection to flag forbidden imports and reflective escape attempts before execution.

Enables deterministic headless operations on AutoCAD 2021 (English) drawings, including inspection, mutation, parametric drawing, topology auditing, preview capture, and validated AutoLISP execution with rollback and security safeguards.

Enables AI clients like Claude Code, Cursor, or VS Code to drive the Unreal Editor: execute Python, capture screenshots, tail logs, check status, and run VERA commands.

Enables local FiveM development by letting an AI assistant execute JavaScript/Lua on the server or client, automate NUI interactions, capture game screenshots, manage resources, and run repeatable tests with screenshot evidence.

An MCP server that lets AI models drive any Coherent Gameface UI over Chrome DevTools Protocol, enabling JavaScript evaluation, screenshots, DOM inspection, console capture, and breakpoint debugging.

Production-ready MCP server for secure Python code execution with artifact capture, virtual environment support, and LM Studio integration.

Lets an AI agent launch or attach to a running Electron app and control it directly over the Chrome DevTools Protocol: capture screenshots (optionally with the native window frame), click, drag, hover, scroll, type, press keys, resize and reload. It also exposes JavaScript execution in both the renderer and main process, an accessibility tree with click-ready coordinates, and console logs, so an agent can inspect and operate the app without adding any code to it.

Enables executing commands in visible VSCode terminal tabs with full output capture, supporting long-running processes, interactive input, and isolated sessions for parallel agents.

Connects Claude Code to local Jupyter kernels for code execution, kernel management, and notebook execution, with security gating and output capture.