"Optimizing AI Model Thinking, Token Usage, and Context Size" matching MCP servers:

Enables AI agents to compare design tokens from multiple sources, retrieve prior reconciliation runs, and get detailed per-conflict breakdowns with confidence factors and alias chains.

Enables an AI assistant to open 3D model files (STL, 3MF, Bambu Studio and OrcaSlicer projects) in a local browser viewer where the user clicks exact spots to leave feedback. Each note comes back with the part name, millimetre coordinates, surface direction and a numbered screenshot, so the assistant can revise the design and show the new version.

Lets coding agents read and write design-system themes and tokens in the locally running editor, with locked tokens protected, and exposes a seven-step design workflow through tools, prompts, and guidance resources. Changes made by the agent appear in the editor within about 1.5 seconds, with reconnection and version-conflict reporting.

Converts Figma designs into structured code context with token-aware styling, enabling AI agents to generate production-level frontend code.

Ask, check and change live Revit models from Claude, Cursor or any MCP client. One undo per change, read-only switch. Revit 2022-2027.

A Model Context Protocol (MCP) server that enhances Figma design integration by adding element position information to API responses, enabling AI assistants to better understand spatial relationships and convert designs to code more accurately.

Converts Lanhu design URLs into AI-ready implementation context including HTML+CSS (Tailwind), image downloads, design tokens, and guidance.

Open, secure runtime that puts Revit, Rhino, Navisworks, and Power BI behind one MCP call center, enabling an AI agent to orchestrate them directly instead of manually dumping data between disconnected apps.

Transforms HTML into Figma designs using only the user’s design system, ensuring correct component usage or safe fallback to primitives, while continuously learning from each build to improve mapping accuracy and consistency.

Loads your project's Tailwind CSS config and exposes tools for AI agents to query actual design tokens and validate class names, preventing hallucination of non-existent utilities.

A read-only MCP server that extracts actual Figma prototype flows, transitions, and per-screen interactions so agents can see navigational behavior rather than infer it. It reports explicit source and destination IDs with warnings for unresolved or ambiguous destinations, without guessing or writing back to Figma.

Enables users to generate rigged, game-ready gun models in Blender from parameterized presets or platforms, including attachments, animation clips, fact sheets, and reference-photo validation.

Enables AI agents to programmatically create, inspect, edit, validate, and headlessly render traditional 2D hand-drawn animation projects, including frames, layers, audio, camera keyframes, spritesheets, and video or GIF exports.

Enables AI agents to read, watch, and edit live Excalidraw rooms by joining as a socket bot over a self-hosted relay, bypassing browser automation.

An MCP server that gives AI coding tools access to Figma design data for accurate one-shot implementation of designs.

An MCP server that gives AI coding agents access to Figma design data, enabling pixel-perfect implementation of designs through structured data extraction, image downloads, and design token retrieval.

Enables AI assistants to control Figma in real-time through Model Context Protocol, allowing design creation, editing, and reading operations directly from VS Code.

Enables natural-language CAD geometry creation in Autodesk Fusion 360 by connecting an LLM running in WSL via OpenCode to Fusion on the Windows host.

MCP server for creating and editing Effekseer effects with AI agents. It provides tools to manage effect documents, nodes, properties, resources, and curves via stdio.

Generate professional AI-powered presentations from a topic, raw text, or document file. Export to PPTX, PDF, image, or shareable link.

Enables external AI assistants and MCP clients to programmatically control Adobe Illustrator via WebSocket, supporting generative vector creation, layer organization, and document automation from natural language prompts.

Lets Claude Code, Cursor, VS Code and other AI agents draw and edit draw.io diagrams from your project's files, on a live browser canvas you can also edit by hand. Includes version history, undo, cloud shape libraries (AWS, Azure, GCP) and PNG or SVG export.

Exposes tools to ingest FigJam boards, retrieve context summaries, and answer free-form questions about the board content.

Read-only MCP server exposing AI Room Design's image generation styles, pricing, FAQ, and official links to MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.

An unofficial MCP server for generating infographics and visuals from text using the Napkin AI API, enabling AI assistants to create professional diagrams, mindmaps, and charts.

Turns AI coding agents into visual creative assistants by providing a curated prompt gallery, prompt enhancement, and image/video generation via LemGen, with free inspiration tools and optional token-based generation.

Enables MCP clients such as Claude Code, Codex, and Cursor to run Textile Designer AI's textile design tools on image files and URLs — upscaling, repeats, background and watermark removal, channeling, colourways, vectorizing, and more — and save the results locally. Handles device-code account login, plan and credit checks, cost estimates, and job status/download for long-running runs.

Enables AI assistants to search design inspiration, generate and edit images and videos, use reference media, remove backgrounds, create product detail images and marketing posters, and access saved creative assets through remote OAuth or legacy local setups.

Provides design capabilities including requirement analysis, visual token extraction, design generation, and visual auditing.

Open-source home design and floor plan editor for AI agents: draw walls and rooms, place furniture, doors and windows, build kitchens and wardrobes, check lighting, ergonomics, electrical and plumbing against building codes, and render the plan, 3D views or photorealistic images. Runs in the desktop app, the browser or the hosted server, and every change can be undone.