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

A demonstration MCP server for exploring MCP prompts with 10 reusable development prompts.

Transforms basic interface ideas into comprehensive, professional-grade UI/UX design specifications with detailed styling, animations, components, and accessibility requirements for websites, apps, and other digital interfaces.

Enables AI coding agents to consult a multi-model deliberation council before irreversible, high-stakes decisions, returning structured architectural decision records with consensus and dissenting risks.

Cloud infrastructure provisioning via natural language. Enables deploying production-ready infrastructure on AWS, GCP, Azure, or Oracle with a single prompt.

A Model Context Protocol server that gives an LLM a structured visual layer to describe what exists and get back a clean, precise SVG diagram instead of ASCII art.

AI-native architecture diagramming for MCP clients (Claude Code, Cursor, Windsurf). The calling agent authors the graph (nodes, groups, edges); Flowgraf validates it, lays it out deterministically with ELK, renders an SVG + Mermaid, and returns a link to a live, editable canvas you can refine by chat, drag, or one-click AI design review. Agent-authored ops — no API key and no LLM cost to the calle

Enables AI agents to edit diagram/graph structures on a live draw.io canvas and manage local versions via snapshots, restore, and export without embedding a separate LLM or polluting the workspace.

A deterministic architecture audit engine for Cursor. It enforces visual Mermaid protocols to prevent LLM hallucinations, ensuring AI modifies code based on strict blueprints.

An MCP server that designs software projects by drafting design documents with an LLM, refining them, answering questions, and creating projects via the AI2DEV API.

BlenderMCP enables Claude AI to directly interact with and control Blender for prompt-assisted 3D modeling, scene creation, and manipulation. It supports object and material control, scene inspection, and execution of Python code through natural language commands.

Enables direct interaction and control of SketchUp through Claude AI using the Model Context Protocol and a TCP socket connection. It allows for prompt-assisted 3D modeling, component manipulation, and the execution of arbitrary Ruby code within the SketchUp environment.

Provides tools for creating, deleting, and querying nodes and edges in Excalidraw diagrams, enabling diagram editing via LLM interfaces.

Serves local architectural context to LLM coding agents over MCP, enabling agents to query complexity, coupling, and layer metrics while deterministic quality gates enforce project invariants through hooks.

Renders Mermaid diagrams in an interactive viewer with pan, zoom, and split-view source editing, enabling LLM hosts to create and edit diagrams through natural language and synchronize updates back to the conversation.

Connects ParaView to LLM assistants via the Model Context Protocol, enabling direct Python code execution and pipeline control within the ParaView GUI.

A tool-augmented LLM system for the full PDDL planning pipeline, improving reliability without domain-specific training.

A knowledge graph MCP server for Moleculer and Go microservice projects that scans codebases, extracts service metadata, seeds Neo4j, and exposes tools for LLM clients to query and understand service architecture.

Enables users to clarify vague goals through Socratic questioning and generate structured technical specifications, using a curated knowledge base and session state without external LLM APIs.

Provides Mermaid code validation and iterative line-level repair to fix syntax errors in LLM-generated Mermaid diagrams, ensuring consistency with the frontend parser.