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

An MCP server that bridges multiple LLMs (OpenAI-compatible APIs and CLI coding agents) for collaborative debugging and diverse AI perspectives.

MCP server for building a user-approved transcript corpus from Handy, optimizing post-processing prompts against LM Studio, and promoting winning inference settings.

An MCP server that lets LLM agents autonomously play retro games by driving a real OpalEmu emulator in a Playwright-controlled browser, exposing tools for loading ROMs, controlling buttons, and capturing screenshots.

Downloads your entire Search Console dataset into a local SQLite database, then gives your LLM a pre-built SQL query library for every standard SEO analysis type, with context available for your LLM to perform any SQL query to answer your questions and analyse for you.

Runs entirely locally to provide calm, animated breathing sessions that open in a browser or as an artifact, with tools for matched or custom sessions, pattern listings, and a breathing-break prompt, while collecting no data.

Daily-refreshed Glama TDQS score tracker for any MCP fleet. Scrapes per-tool grades from glama.ai, stores in SQLite with snapshot history and delta tracking, surfaces via MCP tools, Prefab cards, a 6-page web dashboard, and an LLM-powered chat interface.

Open Ephemeris is a high-precision astrology API with an MCP server exposing 116+ endpoints across natal charts, transits, synastry, Human Design, BaZi, solar returns, and much more.

Enables LLM clients to access and manage Mitti inspections, templates, actions, and users through MCP tools.

Bridges Gitee, China's largest code hosting platform, to MCP for exploring trending repos, searching users/repos, and translating Chinese content with a local LLM.

A lightweight MCP server for managing personal finances locally. It allows users to log transactions, view summaries, manage categories, and interact with their budget via any MCP-compatible LLM client.

A lightweight, self-hosted MCP server that connects LLM-based agents to Red Hat Lightspeed services, enabling natural language querying of read-only (and optionally write) operations across Advisor, Image Builder, Inventory, Planning, Remediations, and Vulnerability services.

An MCP server that connects LLM assistants to LTspice/ngspice circuit simulation, enabling design, verification, and iteration on schematics and netlists with structured numeric results.

An MCP server that provides a toolbox for interacting with EPA SWMM stormwater models, enabling users to analyze model data and interpret results through LLM-driven tools. It assists stormwater modelers in understanding hydraulic systems and modeling behavior using natural language interfaces.