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

A Python-based MCP server that extracts football match data from multiple global sources like ESPN and BBC Sport using intelligent web scraping. It enables AI assistants to retrieve scheduled matches, real-time scores, and broadcasting details with advanced filtering for high-profile games.

Converts messy HTML into clean semantic markdown with integer IDs, enabling LLMs to navigate and interact with web pages efficiently using intent-guided filtering and diff-based updates.

Enables searching free video clips from Mixkit and Pexels while automatically excluding previously used material per project. Supports marking final selections, viewing usage history, and forgetting records to prevent repetition across videos.

Enables users to consult tax clearance certificates (Certidão Negativa de Débitos) from the Sorocaba city government through an official source, with a read-only tool for natural language queries.

A lightweight MCP server that enables LLMs to search the web via DuckDuckGo, search GitHub code repositories, and extract clean content from web pages in LLM-friendly formats.

Enables scraping and comparison of LLM inference pricing from multiple providers like Cloudrift, DeepInfra, Fireworks, and Groq, storing results in a SQLite database.

Enables scraping and comparing pricing information for LLM inference services across multiple providers (CloudRift, DeepInfra, Fireworks, Groq) using Firecrawl API and SQLite storage.

Provides persistent browser tabs with tools to read, click, type, and interact with web pages, enabling local LLM agents to perform multi-step web tasks.

An MCP-native pipeline for collecting structured intelligence on higher education institutions using the WHED schema, enabling scraping, extraction, validation, and saving of profiles.

Enables AI assistants to crawl websites, extract dynamic content, navigate links, and save structured Markdown files via the MCP protocol, with support for anti-bot bypass, CSS selectors, and custom JavaScript execution.

Provides web search and page fetch tools for LLM assistants, extracting content and enabling text search within fetched pages.

Fetch URLs and return clean, LLM-ready markdown with metadata and layered prompt injection defense. Configurable timeouts, word limits, JS rendering, and link extraction. All-in-one MCP server + CLI.

An MCP server for searching the Jurisprudencia de Buenos Aires (JUBA) database for legal summaries and full-text judicial rulings. It enables AI assistants to perform advanced searches across various legal matters from the Supreme Court of the Province of Buenos Aires.

Enables LLM clients to run Brave LLM Context web searches and fetch readable markdown extracts from URLs, including specialized site extraction, PDF text, raw mode, and pagination.

Web Content Retrieval (full webpage, filtered content, or Markdown-converted), Custom User-Agent, Multi-HTTP Method Support (GET/POST/PUT/DELETE/PATCH), LLM-Controlled Request Headers, LLM-Accessible Response Headers, and more.

Search Ukrainian marketplaces (OLX, Hotline, Prom; Rozetka via Bright Data MCP) from a plain-language prompt and get structured offers with prices and links.

Converts web pages and HTML strings into clean, LLM-optimized Markdown with metadata extraction and token estimation. It uses a lightweight, browserless approach to provide token-efficient output for more effective LLM processing.

Autonomous LLM-powered web crawler with 17 browser tools and goal-driven agent. Single Rust binary with stealth browsing, provider-agnostic LLM support, and built-in MCP server.

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 that converts URLs to clean Markdown/Text for LLM agents.