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

MEOK NIS2 De Register - MCP server providing AI-powered tools and automation by MEOK AI Labs

MCP server exposing prompt-shield's prompt-injection firewall for LLM applications. Four tools — scan_input, scan_output, scan_tool_result (with optional sanitization), and list_detectors — backed by 34+ detectors and a federated ed25519-signed threat feed.

The control plane for AI prompts that scores, enforces policy, locks config, and audits every prompt decision.

WAF for AI agents — block prompt injection before it reaches the LLM.

Enables security researchers to evaluate AI system defenses against prompt injection attacks through a comprehensive set of test vectors and analysis tools.

MCP server toolkit with payload library, WAF bypass generator, rate limiter, plugin system, and inter-MCP bridge for security testing.

Exposes an OpenAI- and Anthropic-compatible HTTP, SSE, and stdio gateway that wraps multiple subscription CLIs, adding prompt-injection defense, PII redaction, cost-aware routing, and reasoning-trace capture for MCP-compatible clients like Claude Desktop and Cursor.

Provides a governance gateway for LLM and agent traffic via MCP, blocking prompt injection, redacting PII, enforcing per-tenant token budgets, and caching repeat questions semantically. Enables AI agents to route model calls through the same guardrails instead of calling providers directly.

Provides MCP clients a single decision-only tool to classify prompts as safe for local or cloud models, or as containing PII or jailbreak content, without executing actions or calling AI models.

A standalone MCP server that enforces clean prompt structure, strips model‑invented instructions, and detects capability hallucinations before they propagate through your system.

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.

Enables a cloud orchestrator to query a local Ollama model over Tailscale or a LAN as a side-channel for drafts, summaries, and other helper output, with tools to list available models and to redact text. Answers leaving the server are passed through output-only DLP that masks card numbers, IBANs, emails, phone numbers, API keys, and similar secrets before they reach the cloud.

Enables MCP-compatible clients to deterministically neutralize adversarial prompt injections and jailbreak overrides with zero-dependency, sub-millisecond heuristic analysis.

MCP server that compares a person's identity data in Argentina (DNI, name, birthdate, address) against the registry and returns a similarity score. It is read-only and works with any MCP client, requiring prepaid credits per query.

Compares a person's identity data in Mexico (CURP, name, birth, address) and returns a similarity score against official records. It is a read-only MCP server that works with any MCP client over HTTP.

Enables deterministic detection and neutralization of adversarial prompt injections and override attempts in AI agent workflows via a zero-dependency MCP server, providing structured telemetry and low-latency validation.

Enables LLMs to propose UPDATE/DELETE SQL that is run in a transaction, measured, and rolled back, requiring human approval before applying to prevent unauthorized changes.

A spec-compliant remote MCP server with built-in OAuth 2.1 and Dynamic Client Registration, enabling Notion Custom Agents to connect via 'Sign in with OAuth' without bearer tokens. It supports SSO federation to Google and Microsoft Entra, and includes basic tools like whoami, echo, and slow_task.

Verifies a person's identity in Argentina by cross-checking provided data (DNI, name, birth, and address). Read-only MCP server with one tool, works with any MCP client over HTTP.

Exposes LLM output validation (schema compliance and prompt-injection detection) as an MCP tool, enabling any MCP-compatible agent to apply real-time guardrails without importing the codebase.