"Créer des systèmes de prompt pour les modèles de langage (LLM)" matching MCP servers:

Enables management of structured prompt assets from Figma, including listing, validating, and exporting prompts via the Model Context Protocol.

MCP server to help AI assistants generate Italian PA user interfaces by providing components, recipes, accessibility rules, and validation for Bootstrap Italia and Web Components.

Create designed Figma Slides by chatting with GitHub Copilot or Claude. It generates polished, multi-layout decks with 31 layouts and 17 design systems directly in Figma.

A read-only Figma MCP server for GitHub Copilot that renders screenshots locally inside Figma via exportAsync, avoiding any public S3 URLs or outbound HTTP. It provides 9 tools to inspect Figma files, components, variables, and FigJam boards through a private tunnel.

Connects SketchUp to Claude AI through the Model Context Protocol, enabling prompt-assisted 3D modeling, scene manipulation, and woodworking joinery operations.

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 AI coding assistants to control JLCPCB EDA for PCB automation, exposing 39 tools for component manipulation, routing, copper pour, DRC, and more. Includes a built-in PCB agent for orchestrating multi-step tasks.

Connects Blender to LLMs, enabling prompt-driven 3D modeling, scene creation, and manipulation through natural language.

Connects Claude AI to Houdini via the Model Context Protocol, enabling prompt-assisted 3D modeling, scene manipulation, and rendering within Houdini.

BlenderMCP connects Blender to Claude AI through the Model Context Protocol, enabling prompt-assisted 3D modeling, scene creation, and manipulation.

Connects Rhino and Grasshopper to Claude AI via the Model Context Protocol, enabling prompt-assisted 3D modeling, scene manipulation, and control through tools like object creation, layer management, and code execution.

Enables prompt-driven video editing in Adobe Premiere Pro, allowing Claude to transcribe footage, decide cuts, build motion graphics, and assemble timelines via natural language.

An MCP server that parses CAD files (.dwg, .dxf, .dwf, etc.) via the Cadlens API, enabling LLM clients to extract and reason over entity, layer, and metadata payloads.

Art-directed website prompts delivered as slash commands in Claude Code, Claude Desktop and Cursor: hero sections, landing pages, SaaS, portfolio, e-commerce and 3D/WebGL scenes. Each build is registered as a real MCP prompt and written natively for the tool you are in (Lovable, Bolt, Cursor or Claude), with a live demo you can scroll before spending a token.

Queries Aurum design system components, tokens, icons, Figma node IDs, and changelog via LLM clients.

Generates beautiful Excalidraw diagrams from natural language descriptions using a local llama.cpp LLM, entirely offline.

MCP server that lets an LLM agent drive StableProjectorz, a 3D modeling app, by inspecting the loaded model, app state, viewport screenshots, and triggering UI actions via a loopback socket bridge.

Enables LLM workflows to inspect SVG structure and add SMIL animations such as translation, rotation, scale, opacity, path morphs, and stroke-dashoffset. It returns both animated and static SVG versions for reduced-motion accessibility.

Enables evidence-grounded web design analysis by searching GDWEB references and generating isolated, per-reference DESIGN_INDEX specification documents for LLM-driven frontend development.

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