"Blackmagic Design" matching MCP servers:

Enables AI agents to manage routes on the Design Canvas infinite canvas app, including adding, removing, listing routes, and capturing screenshots of the canvas.

Manages design tokens (colors, spacing, fonts) in a JSON file and enables agents to read, write, export, and detect drift between tokens and CSS via MCP.

Provides read-only access to over 100 UX/UI design checklists from Checklist.design, enabling users to search and retrieve design guidance for specific flows and screens. Runs locally without an API key.

Enables AI coding agents to retrieve mode and stage guidance so they can lead users through a 9-stage design workflow, including questions, required artifacts, exit criteria, dependencies, pitfalls, rollback impact, and environment requirements. It helps non-designers turn ideas into buildable HTML/WPF design specs while keeping the human in control of confirmation and revisions.

Enables coding agents to read ground truth about a React design system — components, props, cva variants, tokens and docs — over MCP so they write UI that matches it. It also exposes a check_ui linter agents run on their own output, returning rule ids, locations and concrete fixes before review.

Enables high-craft web design and engineering through OKLCH color systems, fluid typography, Three.js 3D scenes, frontend security audits, multi-viewport capture, and Python-backed design verification.

Provides software design guidance via MCP, including SOLID principles, design patterns, pattern scaffolding, and heuristic code-smell detection to help review and refactor code.

Enables AI coding agents to search public design-system catalogs and retrieve only the relevant tokens or sections for a chosen brand, so generated UI matches a specified visual style instead of generic AI output.

Provides design pattern templates and anti-pattern guidance to AI coding agents for correct pattern implementation.

Provides deterministic design style recommendations and structured tokens for AI content generation, with 30 curated styles including color palettes, typography, and visual directives.

A local-first FastMCP server that indexes offline frontend catalogs (components, patterns, motion libraries) and exposes discover, search, compare, and recommend tools to AI agents via stdio.

Design contract layer for AI agents. Scans Figma, code, Storybook, and token files, reconciles conflicts, and serves a single machine-readable source of truth so every agent gets the same authoritative design rules before it builds. Local-first.

Enables AI assistants to retrieve and cite South Korean national construction standards (KDS/KCS) with tables and formula images via the KCSC OpenAPI, and to use design decision trees, validation, and blank Excel templates directly in the chat interface.

One-click website design cloning with Puppeteer. Captures HTML, CSS, colors, fonts, and layout structured data for recreation.

Compares Figma frames to live pages, checking colors, fonts, and border radii, and generates a shareable HTML report.

A local stdio MCP server that enables AI coding tools to search and retrieve reusable interactive and motion design parts from a design-notes library, returning each part's notes, anchors, extracted parameters, and the absolute path to its self-contained index.html source. It also serves the original README provenance and source URLs for a given note.

Generates randomized English Markdown frontend design directions using curated catalogs, with optional soft compatibility scoring. Does not call an LLM.

Bridges Claude Code with Claude Design, enabling sending design instructions, reading replies, and pulling generated files into the codebase.

A local MCP server for AI image generation using ComfyUI, Claude Code, and OpenClaw, with a built-in library of over 1,300 prompts for private, fast image creation.

Enables natural language control of Blackmagic ATEM video switchers via the Model Context Protocol. It allows users to manage camera switching, transitions, audio mixing, macros, and streaming operations through AI assistants.

Compare design and implementation screenshots using pixel-by-pixel analysis, generating visual diff images and metrics.

MCP server bridging ChatGPT-compatible clients to the Design Flow System, enabling project session management, draft import, round locking, and read-only access to design state and traceability.

Bridges Design OS exported component packages into target projects, handling migrations across different CSS, component, and icon libraries.

Generates print-resolution business posters (PNG/JPG) from a plain-language brief, using a design system derived from reference posters to lay out text, palettes, and images automatically.

Enables AI assistants to architect and build Awwwards-level websites with spring physics, design systems, React 19 templates, and HD visual inspection.

Maps design components, tokens, and patterns to their code implementations, providing AI coding agents with exact-match resolution across any design tool and framework. Enables agents to reliably discover and reuse existing components across React, Vue, Flutter, SwiftUI, and more.

Enables AI agents to generate dimensionally accurate mechanical parts (gears, enclosures, brackets, assemblies) in headless Blender from plain-English specs or JSON parameters, then verify them against manifold, bounding-box and print-production gates and export glTF/STL assets. It also scaffolds interactive Three.js CAD viewer pages with orbit controls, wireframe toggles and exploded-view scrubbing.

Reverse-engineers design videos and images into structured frontend implementation specifications using vision LLMs and FFMPEG for frame-level analysis.

Enables AI hosts to validate, write to disk, hot-reload, preview, and export single-file HTML prototypes built to the Spark OP design spec, serving them locally at 127.0.0.1:5179 by slug. Also bundles the triggering skill, spec references, templates, and CSS tokens so agents can create, revise, and hand off development-ready prototype HTML through one controlled output path.

Exposes iDRAC design-system knowledge via a single get_component tool, currently returning placeholder data for known components.