mcpField
M
MCP Server Demo - ClienteDB

MCP Server Demo - ClienteDB

Local
github.com/amauryeuzebioDeveloper Tools3Updated 81w ago
Repository

About MCP Server Demo - ClienteDB

MCP Server Demo - ClienteDB is a sample MCP server that connects SQLite customer data to client-management queries. It is intended as a compact demonstration of searching customer records and counting them.

Key features

  1. 01Count registered customers
  2. 02Find customers by partial name
  3. 03Find customers by neighborhood

Use cases

  1. 01Check the total number of customer records
  2. 02Find a customer using part of a name
  3. 03List customers from a specific neighborhood

MCP support

It exposes SQLite customer lookups as MCP tools, including customer counts and searches by name or neighborhood.

#mcp-server#sqlite#client-management

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Server Demo - ClienteDB

Este é um exemplo de servidor MCP que demonstra a integração com SQLite para gerenciamento de clientes.

Funcionalidades

O servidor oferece as seguintes ferramentas:

  1. contar_clientes(): Retorna o número total de clientes cadastrados
  2. buscar_cliente_por_nome(nome): Busca clientes pelo nome (busca parcial)
  3. buscar_clientes_por_bairro(bairro): Busca todos os clientes de um determinado bairro

Como usar

  1. Crie e ative o ambiente virtual:
# Criar ambiente virtual
python3 -m venv .venv

# Ativar ambiente virtual
# No Windows:
.venv\Scripts\activate
# No macOS/Linux:
source .venv/bin/activate
  1. Instale as dependências:
pip install -r requirements.txt # instalar no ambiente virtual

python3.12 -m pip install -r requirements.txt --break-system-packages  # Instalar máquina física
  1. Gere os dados de exemplo:
python generate_sample_data.py
  1. Inicie o servidor MCP:
mcp dev server.py # para usar mcp inspector
mcp install server.py --name "ClientesMCP" # instala o mcp no claude desktop

python mcp_server.py # para usar pelo protocolo sse

Para desativar o ambiente virtual quando terminar:

deactivate

Estrutura do Banco de Dados

A tabela clientes contém os seguintes campos:

  • id (INTEGER, PRIMARY KEY)
  • nome (TEXT)
  • email (TEXT)
  • telefone (TEXT)
  • bairro (TEXT)
  • endereco (TEXT)

Bairros Disponíveis

Os dados de exemplo incluem clientes nos seguintes bairros:

  • Centro
  • Jardim América
  • Vila Nova
  • Bela Vista

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.