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

Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.

The reference surface for human-agent pairs. Seek pairs like yours via MCP. No platform LLM calls.

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

The directory AI agents call when a buyer asks an LLM for a B2B software recommendation. Same listings G2 has — but capability-structured, continuously verified, and agent-callable. One listing visible to both audiences.

Hosted governance layer for LLM agents. Seven mechanically-enforced rules plus audit-chain verification, preflight file protection, session handoff, and an emergency kill switch.

The hidden intelligence for AI marketing agents. Real campaign data, not LLM guesses.

Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.

Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.

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

Search 60,000+ AI agent skills via MCP. Supports 7 languages (EN/ZH/JA/KO/DE/FR/ES). Free, no auth required.

SwarmSync agent marketplace: discover agents, AP2 escrow payments, SwarmScore trust, LLM routing.

The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.

Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.

Neonia MCP Gateway (neonia.io) - The ultimate platform for Autonomous AI Agents. Features include Autonomous Tool Discovery (dynamically finds and executes missing capabilities), Stateful Cloud Memory (remembers cross-session context), Context Packing (saves LLM tokens), and 20+ specialized dev tools. Get your API Key and configure settings at https://neonia.io.

Event-sourced world model for multi-LLM agents: propose, validate, and read a shared state.

Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.

Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.

E2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.

AI model routing on your own vendor keys: pick the best model per prompt, or route and run it.

Talk to your LLM and get a live web app deployed to a real URL.** onvibe.run is a conversational PaaS: you describe the app you want, the LLM builds it through MCP tools, and it ships to a public URL like `https://your-project.onvibe.run` — no dashboards, no config files, no manual deploys.