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

Evidence-gated task verification for AI agents. Decompose goals into acceptance criteria, attach proof (screenshot, curl, file), independent LLM judge accepts or rejects. 24 tools. Hosted remote MCP (streamable-http, OAuth 2.1 + DCR).

Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

Display delivery platform for AI agents. Push HTML, dashboards and live data to screens.