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

Enables LLMs to search Picnic's grocery catalog, manage the shopping basket, and select delivery slots for Picnic's grocery service in Germany and the Netherlands.

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.

Provides a local MCP interface to query captured, PII-scrubbed prompt telemetry from coding agents and browser chats, enabling time summaries, prompt search, and activity analysis without data leaving the machine.

Blind multi-model councils with anonymous LLM seats and direct 1:1 chat as a local MCP server. Enables asking one question to get independent answers from multiple model CLIs, then blind scoring and reveal.

Enables dynamic prompt management by automatically discovering and serving markdown prompt files with YAML frontmatter via the Model Context Protocol.

Enables a primary agent to offload bounded, high-volume analysis of explicitly selected workspace files to an auxiliary LLM through a single read-only tool, returning text, Markdown, JSON, or unified-diff output with token usage while retaining all planning, verification, and edits.

MCP server providing on-demand access to official prompting guides for building robust meta-prompts.

MCP server that provides tools for evaluating LLM agent reliability, including adversarial task generation, automated LLM-as-judge assessment, and confidence statistics.

An MCP server that runs curated adversarial prompts against local Ollama models to test guardrails, scoring responses with heuristic verdicts for human review.

Serves an LLM-maintained markdown wiki to agents over MCP, providing tools for querying and navigating wiki pages without direct filesystem access.

Enables cloud-based MCP clients to delegate privacy-sensitive or large-output tasks to a local LLM, returning sanitized placeholders or digested summaries so private data never leaves the user's network.

A thin MCP server that delegates lightweight tasks from Claude Code or any MCP-compatible client to local or cloud LLMs via LiteLLM, supporting models like Ollama and cloud APIs as subagents.

Daily-verified LLM API pricing dataset (44+ models, CN & global) with a hosted MCP server for live price queries and token cost estimation.

A local MCP gateway that unifies multiple LLM providers, API keys, routing, and multi-model discussions into a single tool surface.

Monitors brand mentions, citations, sentiment, competitor share of voice, and GEO performance across AI search engines.

An MCP server for a plain-markdown LLM wiki vault with YAML frontmatter and Obsidian-style wiki-links, enabling headless full-text search, note reading, backlink discovery, and safe append/create-only writing with path traversal protection and an immutable raw/ directory.

Community-driven library of tested prompts for AI agents, enabling search, retrieval, sharing, and rating of prompts.

A local-first, multi-provider cost meter for LLM usage, exposed as MCP tools. Captures every call into a local SQLite ledger and lets any coding agent query spend, compare providers, and get recommendations — no cloud, no account. First-class support for Chinese providers (Qwen, DeepSeek) alongside Anthropic and OpenAI.

Enables natural language query and ingestion of wiki knowledge bases built from documents, powered by Claude Agent SDK skills.