wazza-mcp-test-server
A simple HTTP server to validate MCP infrastructure for the Wazza MCP client, exposing endpoints for tool discovery and calling.
README
Wazza MCP Test Server
Servidor HTTP simples para validar a infraestrutura MCP do Wazza como cliente MCP. Ele expõe endpoints HTTP simples para descoberta e chamada de ferramentas e também aceita MCP JSON-RPC 2.0 via POST /, permitindo testar o fluxo de cadastro, tools/list, persistência, exibição, tools/call, retorno ao IA Agent e observabilidade/replay no Wazza.
Stack
- Python 3.11+
- FastAPI
- Uvicorn
- Pydantic
- Docker
Ferramentas disponíveis
echo: repete o texto enviado.get_business_hours: retorna o horário de atendimento.calculate: calcula expressões aritméticas simples com+,-,*,/e parênteses, sem uso deeval.
Instalação local
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Execução local
PORT=8080 uvicorn app.main:app --host 0.0.0.0 --port 8080 --reload
A aplicação ficará disponível em http://localhost:8080.
Deploy no Railway
- Crie um novo projeto no Railway apontando para este repositório.
- Confirme que o Railway detectou o
Dockerfile. - Defina a variável de ambiente
PORTse necessário. O servidor usaPORTe faz fallback para8080. - Faça o deploy.
- Cadastre a URL pública gerada pelo Railway na tela de Integrações de IA do Wazza.
Interfaces suportadas
O servidor mantém duas formas de integração:
- Endpoints HTTP simples:
GET /para health check.POST /tools/listpara listar ferramentas.POST /tools/callpara chamar uma ferramenta.
- MCP JSON-RPC 2.0 via
POST /para clientes que enviam os métodos MCP diretamente para a raiz do servidor.
Exemplos curl
GET /
curl http://localhost:8080/
Resposta esperada:
{
"status": "ok",
"server": "wazza-mcp-test-server"
}
POST /tools/list
curl -X POST http://localhost:8080/tools/list
POST /tools/call echo
curl -X POST http://localhost:8080/tools/call \
-H 'Content-Type: application/json' \
-d '{"name":"echo","arguments":{"text":"Olá mundo"}}'
POST /tools/call get_business_hours
curl -X POST http://localhost:8080/tools/call \
-H 'Content-Type: application/json' \
-d '{"name":"get_business_hours","arguments":{}}'
POST /tools/call calculate
curl -X POST http://localhost:8080/tools/call \
-H 'Content-Type: application/json' \
-d '{"name":"calculate","arguments":{"expression":"5 * (3 + 2)"}}'
Resposta esperada:
{
"content": [
{
"type": "text",
"text": "25"
}
]
}
POST / MCP JSON-RPC initialize
curl -X POST http://localhost:8080/ \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'
Resposta esperada:
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"protocolVersion": "2024-11-05",
"capabilities": {
"tools": {}
},
"serverInfo": {
"name": "wazza-mcp-test-server",
"version": "1.0.0"
}
}
}
POST / MCP JSON-RPC tools/list
curl -X POST http://localhost:8080/ \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'
POST / MCP JSON-RPC tools/call
curl -X POST http://localhost:8080/ \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"echo","arguments":{"text":"Olá"}}}'
Resposta esperada:
{
"jsonrpc": "2.0",
"id": 3,
"result": {
"content": [
{
"type": "text",
"text": "Olá"
}
]
}
}
Erros
Erros de ferramenta retornam o formato:
{
"error": {
"code": "tool_error",
"message": "Descrição do erro"
}
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.