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

Enables vision-capable AI clients to read and adjust Capture One on macOS through local MCP stdio or JSON CLI, including curves, color tools, film grain, masks, reference matching, and real previews of rendered edits.

Enables vision-capable AI clients to read and adjust Capture One on Windows through an MCP stdio server (plus a JSON CLI), applying exposure, curves, color, layer and mask edits and returning real Capture One-rendered previews. It runs a local bridge to C1's native parameters with no presets, screenshots or synthetic input.

Enables generating UI design rules, fetching color palettes, and retrieving brand design references from over 328 brands.

Enables controlling a game character, drawing on a canvas, and running chemistry experiments via natural language commands to Claude.

Enables driving Inkscape headlessly from an MCP client, with verified SVG editing, rendering, optimization, and animation tools.

An MCP server that provides AI tools with relational tech principles, patterns, and the Studio library to guide builders in creating community-centered tools using embedded design.

Enables an MCP-capable AI client to drive a locally installed, licensed Autodesk Inventor through its COM API for local modeling tasks. It supports creating and updating a rectangular plate and a parametric quickchanger concept assembly, opening and inspecting parts and assemblies, and returning viewport previews.

Local MCP server inside 8 Autodesk apps (Revit, AutoCAD, Civil 3D, Advance Steel, Navisworks, Inventor, 3ds Max, Robot; 2023–2027): 480+ read/write actions, one-click setup for Claude, ChatGPT/Codex and Cursor. Commercial, free 14-day trial. Formerly HMK Pilot.

Gives Claude full read/write control of a live Graphisoft Archicad 26 project through roughly 260 tools, spanning modeling, drafting, annotation, queries, documentation and exports. Also lets the model capture views to visually verify its work, with batched edits, strict validation and access to the official JSON API.

An MCP server for Moho Pro 14 that lets MCP clients inspect documents, edit layers and animation, render frames, capture the Moho window, and send mouse or keyboard input.

Lets an AI agent drive a browser-based CAD application by forwarding tool calls to the page's own modeling registry, so it can open documents, run programs, select geometry, load skills, and capture screenshots. Also exposes the same tools through a CLI for agents that only have a shell.

A local-first MCP adapter for Vicon Shogun Post that provides read-only inspection of motion-capture scenes, including subject markers and trajectory queries via the official SDK.

Enables AI assistants to query SketchUp models, extrude massing volumes, configure solar shadows, and capture viewport renderings through MCP tools.

Connects AI assistants to Rhinoceros 3D and Grasshopper, enabling generative NURBS geometry, parametric definition solving, layer manipulation, and viewport capture.

Enables coding agents to scaffold, preview, inspect, navigate, capture, and build interactive HTML presentations authored as React/TSX source files. It operates the local presenter—keys, step tabs, URLs, and tools share one position—while agents edit the source directly.

Enables ChatGPT to initiate a visible, evidence-backed UI/UX audit by returning an exact workspace URL through a read-only start_audit endpoint, where page-scoped Site Tools can measure and judge the target without claiming capture.

Enables AI agents to connect to Autodesk 3ds Max via the Model Context Protocol, allowing natural-language control of scene creation, modeling, materials, viewport capture, and plugin introspection through dedicated MCP tools.

Enables MCP-connected assistants to turn a natural-language brief into a complete, polished, responsive landing page by owning design strategy, HTML generation, composition validation, Chromium rendering, screenshot capture, and an audit manifest. Exposes just three production tools for generating and building pages and inspecting capabilities, so the connected model only has to translate intent into a brief and critique the rendered result.

Enables creative software agents to operate within bounded, temporary workcells, handling scored objectives through autonomous inspect, execute, capture, and correct loops while producing evidence-backed receipts for human review.

An MCP server that enables AI assistants to browse Storybook components, manage stories, inspect props, and capture screenshots of components.

Enables AI agents to automate the PlayCanvas Editor, from project and scene management to entity, script, asset, and build operations. Agents can also launch the running app to capture screenshots, read logs, and send input to confirm scenes actually work.

Local MCP server providing a curated 201-card design reference library with natural-language style search, structured filtering, card retrieval, theme borrowing, and capture tooling — all private and offline.

Enables AI agents to inspect and edit Three.js scenes, materials, shaders, lights, animations, and performance in real time, preview changes live in the browser, capture frames, and turn approved changes into code. It supports vanilla Three.js and React Three Fiber across WebGL/WebGPU without modifying the project.

Enables AI agents to automate 嘉立创 EDA Professional through MCP, including schematic and PCB editing, component search and placement, net routing, DRC, and design capture.

Enables users to capture TouchDesigner node network screenshots and ask Claude for context-aware analysis, diagnosis, and suggestions via MCP tools.

Enables natural-language-driven architectural modeling across SketchUp and Blender, including native geometry creation, editable asset work, topology and clearance checks, project-state tracking, evidence capture, and rollback recovery.

It enables Codex to inspect active Blockbench projects, capture viewports, make reversible draft edits, and connect geometry while preserving dimensions, groups, bounds, and Undo behavior.

Enables AI agents to generate images from HTML/CSS, capture URL screenshots, and manage reusable templates through the RendShot API. Provides tools for rendering visual content programmatically within AI workflows.

Deterministic "Rack-as-Code" 3D/2D CAD planner, 5-stage physical/PoE/acoustic validator, and parametric OpenSCAD/STL 3D-print generator for 10-inch mini-racks and 19-inch homelabs.

Search, view, add, diff and update labsUI React components in a Next.js + Tailwind v4 project, and check its setup with doctor. Components are copied into your repo as plain TSX you own.