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

Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus t

Measured latency & uptime for AI inference APIs, by region. Exposes a get_ai_api_latency tool.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith

Cloudflare Workers MCP server: llm-output-quality-monitor

Track Keito time entries and LLM costs from AI agents.

Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.

PII scanning and redaction receipts for LLM traces and tool payloads.

AI visibility monitoring. 24 tools, 8 LLM platforms, Hallucination Guard. Free tier.

Website performance monitoring: scans, Core Web Vitals, RUM data and alerts.