Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.
MCP server
Original text · EnglishCustomer support, live chat, CRM and helpdesk on Crisp with the full official REST API v1 (api.crisp
https://github.com/mcp-dir/crisp-mcp
remote (streamable-http): https://api.mcp.ai/p_crispRepublished in full under its license, with attribution. The source is authoritative.
Atendimento ao cliente, chat ao vivo, CRM e helpdesk no Crisp com a REST API oficial v1 completa (api.crisp.chat), conversas e mensagens, contatos/pessoas, base de conhecimento (artigos, categorias, idiomas), campanhas, operadores, visitantes e configurações do site. Consulta e operação. Autenticação por par de tokens (gerado no Crisp, em Settings, Workspace settings, Advanced configuration).
[English version](README.en.md) · [Documentação completa](docs/) · [Skill pra agentes](skills/)
A Anthropic unificou a instalação de MCPs em claude.ai/customize/connectors. O mesmo link serve pra Claude Web e Claude Desktop (basta estar logado):
Manual (se o deeplink não abrir): claude.ai/customize/connectors → + → Adicionar conector personalizado → cole Nome Crisp e URL https://api.mcp.ai/p_crisp.
[➕ Instalar Crisp no Cursor](cursor://anysphere.cursor-deeplink/mcp/install?name=crisp&config=eyJ1cmwiOiJodHRwczovL2FwaS5tY3AuYWkvcF9jcmlzcCJ9)
[➕ Instalar Crisp no VS Code](vscode:mcp/install?name=crisp&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.mcp.ai%2Fp_crisp%22%7D)
Funciona em qualquer cliente MCP que suporte MCP over HTTP. A URL do servidor é sempre:
https://api.mcp.ai/p_crisp
Detalhes por cliente: [INSTALL.md](INSTALL.md).
Liste as conversas abertas do meu website Crisp
Quais contatos novos entraram esta semana?
Mostre os artigos publicados na base de conhecimento
| Tool | Descrição |
|---|---|
search_tools | Single entrypoint for MCP catalog. |
Detalhe de cada tool: [docs/ferramentas.md](docs/ferramentas.md)
Grátis.
O servidor é open source?
O servidor é proprietário (hosted). Este repositório é o wrapper público com manifestos, docs e skills — tudo MIT.
Posso usar com agente próprio (não Claude/Cursor)?
Sim — qualquer cliente que suporte MCP over HTTP. URL: https://api.mcp.ai/p_crisp.
MIT — veja [LICENSE](LICENSE). O servidor MCP em api.mcp.ai/p_crisp é proprietário (hosted); este repositório (manifestos, docs, skills) é MIT.
| Description | Customer support, live chat, CRM and helpdesk on Crisp with the full official REST API v1 (api.crisp |
|---|---|
| Version | 0.1.0 |
| Packages | None stated |
| Environment variables | None stated |
| Remote endpoints | streamable-http https://api.mcp.ai/p_crisp |
A structured output agent demonstrating Pydantic schema-based responses for customer support ticket creation.
Sourcegithub.com/Shubhamsaboo/awesome-llm-apps/tree/main/ai_agent_framework_crash_course/openai_sdk_crash_course/2_structured_output_agent/2_1_support_ticket_agent
A tutorial demonstrating how to implement a structured customer support ticketing system using Google's ADK (Agent Development Kit) framework. This example shows how to create type-safe, structured support tickets with priority levels, categories, and resolution estimates using Pydantic schemas and
Sourcegithub.com/Shubhamsaboo/awesome-llm-apps/tree/main/ai_agent_framework_crash_course/google_adk_crash_course/3_structured_output_agent/3_1_customer_support_ticket_agent
This Streamlit app implements an AI-powered customer support agent for synthetic data generated using GPT-4o. The agent uses OpenAI's GPT-4o model and maintains a memory of past interactions using the Mem0 library with Qdrant as the vector store.
Sourcegithub.com/Shubhamsaboo/awesome-llm-apps/tree/main/advanced_ai_agents/single_agent_apps/ai_customer_support_agent
Using Tool Required for Customer Service The ChatCompletion endpoint now includes the ability to specify whether a tool must be called every time, by adding tool_choice='required' as a parameter. This adds an element of determinism to how you build your wrapping application, as you can count on a to
Sourcegithub.com/openai/openai-cookbook/blob/main/examples/Using_tool_required_for_customer_service.ipynb
Creating a Customer Service Agent with Client-Side Tools In this recipe, we'll demonstrate how to create a customer service chatbot using Claude 3 plus client-side tools. The chatbot will be able to look up customer information, retrieve order details, and cancel orders on behalf of the customer. We
Sourcegithub.com/anthropics/claude-cookbooks/blob/main/tool_use/customer_service_agent.ipynb
Curated collection of AI agent use cases across industries (incl. Customer Service, E-commerce) with links to open-source implementations, e.g. a LangGraph customer-support agent tutorial.
Sourcegithub.com/ashishpatel26/500-AI-Agents-Projects