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

Searches and retrieves German federal legislation from NeuRIS, the official legal information portal, providing verifiable ELI identifiers and German citations.

Model Context Protocol (MCP) server for German Electronic Invoicing (ZUGFeRD 2.x / XRechnung 3.x). Provides tools to validate, generate, parse, and convert invoices compliant with EN 16931 and KoSIT.

Enables coding agents to inspect Python applications, research source and target models, and produce reviewable migration plans with evidence gates and evaluation before production code changes.

MCP server for community-driven prompt voting and discovery — submit, upvote, and find the best AI prompts.

Proxies LLM completion requests to OpenAI-compatible providers via MCP tools.

Enables MCP clients to scan local GGUF models, estimate VRAM and suggest GPU offload layers, manage llama-server lifecycle, and proxy OpenAI-format chats with idle auto-unload.

Optimizes token costs by intelligently delegating low-complexity tasks to local LLMs via LiteLLM, enabling cost-effective development workflows.

Exposes llm-behave's behavioral regression testing as MCP tools, allowing offline semantic similarity checks on LLM outputs without any API calls.

Estimates GPU requirements, training/inference costs, and cloud-vs-on-prem TCO for AI workloads using deterministic calculators.

Provides a lightweight personal knowledge base MCP server that compiles raw materials into interconnected Wiki pages, with hybrid search (BM25, optional vector, link expansion) and tools for querying, reading, writing, and ingesting content.

An MCP server that provides AI assistants with long-term semantic memory using a Markdown-based knowledge base with hybrid search (vector + FTS5) and syntax-aware chunking. It supports idempotent ingestion, project isolation, and integrity linting.

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

Analyzes, refines, and optimizes prompts for AI assistants by fixing grammar, improving clarity, applying best practices like chain-of-thought and few-shot learning, and scoring prompt quality across multiple dimensions.

Model Context Protocol (MCP) server for Mexican Electronic Invoicing (CFDI 4.0, Complemento de Pagos 2.0). Provide tools to validate, generate, and explore API specifications for SAT/PAC interoperability.

Unofficial MCP server for the messdienst24.de utility portal, providing tools to retrieve heating and hot-water consumption data, download PDF reports, and compare usage trends.

A fully offline MCP server for token estimation, prompt compression, model routing, and semantic caching to optimize LLM usage costs and efficiency.

Enables natural language, read-only access to the SPA system of the Prefeitura Municipal de Teresina, allowing users to query process boxes, urgent deadlines, recent entries, triage briefings, and judicial documents via pure HTTP without a browser.

MCP server and CLI for EVA FING (Moodle of Facultad de Ingeniería, UdelaR) that authenticates headlessly via Shibboleth, enabling AI agents and users to query courses, announcements, activities, calendar, and study material.

Multi-source academic paper search, citation graph exploration, and PDF download as an MCP server, designed for LLM agents doing research.

A Model Context Protocol server that provides LLM Agents with a comprehensive toolset for IP geolocation, network diagnostics, system monitoring, cryptographic operations, and QR code generation.