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

Provides strategic dialogue management and emotional de-escalation for customer support bots, detecting problem patterns and recommending actions like escalation to a human operator.

MCP server for Zammad that focuses on workflows the standard Zammad API tooling does not cover well — primarily shared drafts with strict reply-HTML validation, fresh signature rendering and German-localised quote blocks.

Um servidor MCP omnichannel que integra WhatsApp, LLM, bancos de dados e edge agents, permitindo orquestração de ferramentas e respostas de voz.

Enables AI agents to prompt users for input directly within the chat UI using MCP's elicitation capabilities, allowing for interactive multi-turn conversations without leaving the conversation interface.

Enables LLM agents to operate WhatsApp through the Evolution API, providing tools to list groups, fetch message history, and send text messages to groups or individual phone numbers.

A prompt-injection-aware MCP server demonstrating guardrails for agentic tool use, including permission tiers, untrusted-content quarantine, and heuristic injection detection, with a fictional ticket-triage assistant.

MCP server to manage GestSup tickets via an LLM, with tools for creating, reading, commenting, and searching tickets.

Official remote MCP server for Lobby, the bilingual AI receptionist. Five free no-auth tools: business phone scripts and IVR menus (English + Mexican Spanish), ElevenLabs agent system prompts, missed-call cost math, and a hire-a-receptionist verdict.

A local MCP server that lets any LLM agent manage Pine AI tasks — negotiate bills, cancel subscriptions, resolve disputes, and make phone calls on your behalf.

MCP Server for automated conversational phone calls using Asterisk with Speech-to-Speech capabilities, allowing users to make phone conversations as easily as writing a prompt.

Enables Claude to manage customers and support tickets through database-backed CRUD tools, contextual customer and knowledge resources, and a reusable ticket-triage prompt.

Integrates with Red Hat APIs to enable searching Knowledge Centered Support (KCS) solutions, retrieving solution details, searching support cases, and obtaining case details through LLM applications.

MCP server that wraps the Evolution API (WhatsApp) as semantic tools for LLM agents, enabling messaging, chat management, group operations, and instance control via natural language.

A versatile MCP server providing tools for arithmetic operations, n8n webhook integration, and access to a customer support playbook resource. It also includes specialized prompt templates for converting webinar transcripts into engaging blog posts.

Provides a versatile MCP server with calculator tools, webhook integration for n8n workflows, a customer support playbook resource, and a webinar-to-blog prompt template.

Connects AI agents and LLM clients to a 3D printing studio to manage orders, printer fleets, slicing and quoting, shipping waybills, customer conversations, and analytics.

Enables secure support-ticket and customer-account operations with signed JWT authentication, prompt-injection and tool-poisoning guardrails, and human-in-the-loop confirmation for destructive actions.

Enables LLM agents to handle e-commerce customer support by searching a product catalog and FAQ knowledge base with hybrid retrieval, plus managing orders, carts, returns, shipment tracking, and human escalation through support tickets.

Enables LLM agents to conversationally query and operate a ManageEngine ServiceDesk Plus instance over its v3 REST API, covering tickets, changes, problems, projects, tasks, assets, people, knowledge-base articles, contracts and reference data. Auth is provided via technician API key or OAuth token, with a generic passthrough for reaching endpoints that are not yet wrapped.

Enables agents to navigate users through pre-defined decision trees by submitting answer labels, returning deterministic next instructions without extra LLM calls. Supports domain-independent procedural workflows with state tracking, handling of unknown responses, and a read-only Web UI.