"Resources or information on analysis techniques or methods" matching MCP servers:

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

Exposes surface-bound annotations placed on a Blender model to AI agents, letting them read pending change requests with stable IDs, revisions, positions and visibility, then submit completion summaries by marker ID after editing. This enables batch, review-oriented workflows where the user approves or rejects each agent change in Blender, without requiring object selection, screenshots, or a fixed port bridge.

Bidirectional MCP bridge enabling AI assistants to draw UI on Figma canvas and read designs back as structured data or code tokens via localhost, requiring Figma Desktop.

A visual designer pen for Claude Code that lets users click, drag, or draw on webpages to get source code locations and screenshots for direct editing and verification.

AI design fidelity — compare Figma designs or screenshots against the rendered implementation and get structured discrepancies. Uses your Claude Code or Codex subscription, no API keys.

Search the Keyline Icons set by name and fetch any icon's SVG source or React import, in four styles with rounded or sharp corners. Runs locally, no key needed.

Enables local creation, inspection, revision, and rendering of editable Apple Icon Composer .icon documents from static SVG or PNG artwork, with native appearance previews on macOS.

Enables an AI agent to join a live Excalidraw collaboration room as a headless participant, read the drawing in real time, and add or modify elements on the shared canvas.

Deterministic HVAC duct sizing for agents: size one run or a whole supply, return, exhaust, or outside-air network from terminal CFM, and grade existing round, rect, or oval ducts. Local stdio, no CAD host or API key needed.

Enables controlling a local Blender instance through natural language or code, allowing arbitrary Python/bpy execution and querying scene or object information via MCP.

Enables AI agents to generate on-brand visuals from ideas, URLs, documents, or PDFs in over 100 formats and 150+ languages, with consistent brand kits.

An MCP server that gives coding agents a design brief and a pass or fail UI check. Published on PyPI and the official MCP Registry.

It lets AI coding agents look up design tokens, component specifications, and prohibition rules on demand, then validate generated HTML or JSX with the same lint logic used by CI and editor hooks so violations are caught and corrected immediately. It also exposes the design constitution and rule sets as resources for reference during generation.

Provides UI architecture analysis for converting Figma designs or web pages into reusable UI code blocks with effort estimation in CSV format.

Enables Claude AI to extract design information from Figma files and create or update designs via a Figma plugin, supporting both readonly and write modes.

A self-hosted MCP server that lets Claude (or any MCP client) drive Autodesk Fusion 360 on your own machine.

An MCP server for Adobe After Effects that enables AI assistants to create premium showreels with professional motion design techniques.

A design knowledge MCP server that Claude can query when generating UI, covering eight layers: principles, patterns, content design systems, research methods, service design, brand/visual, business strategy, and design tokens.

An MCP server that enables natural language control of Steinberg Dorico music notation software through Claude Desktop or ChatGPT, offering tools for score creation, note input, notation, harmony analysis, and orchestration.

Offline whiteboard with a local MCP server: an agent draws and edits shapes, connectors, tables, Mermaid diagrams and icons on a board (27 tools). Works on .inkboard files, or on the board open in the Inkboard desktop app.

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.

Lets Claude drive the Affinity design app on macOS like a person would, taking screenshots and then clicking, dragging, typing, pressing shortcuts, and choosing menu items. Works with any Affinity version or studio without API keys or plugins.

Drives the real Claude Design web app from your editor or agent, enabling creation, iteration, and retrieval of designs generated on your own claude.ai account via automated browser interaction.

Enables AI coding agents to read Figma frames, components, or links as compact code-oriented specs with downloadable SVG/PNG assets, and to create or edit Figma content such as frames, text, auto-layout, components, variables, annotations, and prototypes (79 tools). It connects a local WebSocket relay and Figma plugin to the agent, keeping everything private on localhost.

Enables AI assistants to create and edit pixel art and sprite animations by driving Aseprite's 73 tools for sprites, layers, frames, cels, drawing, selections, palettes, tags, slices, tilemaps, filters and export, with a generic escape hatch to any of its 183 menu commands or Lua scripting API. It runs either headless in batch mode on files or live against an open Aseprite window so edits are visible and undoable.

Enables AI assistants to import Canva share links as editable templates, read and update template layers (text, images, positions, styling), and render PNG, JPEG, WebP, or PDF variants from data — singly or in bulk up to 25 at a time. Connects via a remote OAuth endpoint, API key, or local stdio.

Connects MCP clients such as Claude Code, Cursor, and Codex over stdio to a real vector design canvas in the browser or desktop app, letting agents create, read, edit, and export designs while users collaborate directly on the canvas. Communication stays local on 127.0.0.1, with tools for HTML/Blueprint editing, image generation, vectorization, and background removal.

Provides a hosted remote connection to Mobbin's library of real-world app and web design references over Streamable HTTP, requiring nothing to install or run locally. Access is authorized through an OAuth browser sign-in on first use, with per-client setup and tool listings documented externally.

Enables MCP-compatible AI clients to connect to Autodesk Revit sessions, discover and call native modeling and documentation tools, execute C# or Python inside Revit, and inspect change history or model snapshots.

Serves curated, offline design knowledge over MCP — UX principles, UI patterns and checklists, design-system tokens that can be merged, brand and content systems, research methods, metrics frameworks, and the GOV.UK Service Standard — so clients can retrieve guidance, search the catalogue, and score a described design against it. Everything ships locally with no network, API key, or state.

Lets users pin elements on live web pages, describe desired changes, and send those annotations to coding agents. Agents receive the selected targets, notes, screenshots, and source or style context needed to implement the edits.

A Model Context Protocol server that exposes a versioned brand package (tokens, rules, recipes, media rights, and audit gates) as resources, tools, and prompts for AI agents. It enables agents to plan and audit on-brand UI, image, motion, and video outputs while remaining read-only and credential-free.

Enables AI assistants to create low-poly 3D art for Kenney Shape by drawing on a tile canvas, previewing extruded models, and saving projects or exporting GLB, OBJ, SVG, and PNG files.

Enables MCP clients to inspect, edit in memory, rebuild, render, and export SOLIDWORKS 2016+ parts, assemblies, and drawings on the same PC or in a Windows VM. It provides 13 tools with read-only defaults and controlled export/save behavior.

A local MCP server that lets coding agents turn conversational prompts into deterministic, re-runnable recipes for 3D objects, walkable worlds, and playable games, all stored on your own disk without API keys or cloud rendering. Those recipes can be edited in place and exported to the browser, Godot, Unity, Unreal, Blender, glTF/OpenUSD, or print-ready STL and 3MF at true scale.

Enables AI agents and users to create, inspect, and edit design and diagram Papers on a shared browser canvas. Supports editable plain files, comments, measurements, exports, and sharing across local or project libraries.

Lets Claude draw in and inspect the AutoCAD session already running on a Windows PC by attaching over COM, so no add-in or restart is needed. Provides 32 tools for drawings, layers, geometry, dimensions, blocks, queries, view capture and PDF plotting, with an edit guard, busy guard and one undo step per tool.

Enables users to create and edit 3D floor plans conversationally, describing rooms and layouts or uploading DWG/PDF drawings, then view them in 2D/3D via a live link.

Enables MCP-capable agents to read, edit, lay out, draw, and inspect shapes on a live tldraw canvas without model calls or API keys.

It exposes five streamable-HTTP tools that add service and FAQ information, Figma or URL-to-DX component generation, session-based user identity lookup, and diagnostics to an existing DX IQ deployment.