VIGÍA HACCP MCP Server

VIGÍA HACCP MCP Server

Enables users to generate complete HACCP analyses enriched with real FDA recall data, with tools for process step schema, recall search, and analysis export.

Category
Visit Server

README

VIGÍA HACCP MCP Server

Servidor MCP que genera análisis HACCP completos, enriquecidos con datos reales de retiros de mercado de la FDA (openFDA).

Compatible con: SurfSense, Claude Desktop, cualquier cliente MCP estándar (SSE).


Estructura del proyecto

vigia-haccp-mcp/
├── server.py                  # Punto de entrada — FastMCP + 3 herramientas
├── models.py                  # Modelos Pydantic compartidos
├── services/
│   ├── openfda.py             # Cliente openFDA con manejo de errores
│   └── haccp_generator.py     # Lógica HACCP (PCCs, peligros, límites…)
├── exporters/
│   └── excel_exporter.py      # Exportación Excel con formato profesional
├── requirements.txt
├── .env.example
└── README.md

Herramientas MCP expuestas

Herramienta Cuándo usarla
get_process_step_schema Primero — obtén el schema para construir los pasos
search_fda_recalls Diagnóstico de peligros reales en FDA
generate_haccp_analysis Análisis completo → JSON + Excel

Instalación local

# 1. Clonar y entrar al directorio
cd vigia-haccp-mcp

# 2. Crear entorno virtual
python -m venv .venv
source .venv/bin/activate        # Windows: .venv\Scripts\activate

# 3. Instalar dependencias
pip install -r requirements.txt

# 4. Configurar variables de entorno
cp .env.example .env
# Editar .env si es necesario

# 5. Iniciar el servidor
python server.py
# → Escuchando en http://0.0.0.0:8000/sse

Conectar a SurfSense

  1. Inicia el servidor: python server.py
  2. En SurfSense → Settings → MCP Servers → Add Server
  3. Configura:
    Name:      VIGÍA HACCP
    URL:       http://localhost:8000/sse
    Transport: SSE
    
  4. Guarda y verifica que aparezcan las 3 herramientas en el panel de tools.

En producción (Railway / VPS)

URL: https://tu-dominio.railway.app/sse

SurfSense puede conectarse a servidores remotos siempre que el endpoint /sse sea accesible públicamente.


Flujo de uso en SurfSense

Usuario: "Genera el análisis HACCP para jamón cocido rebanado"
    ↓
SurfSense LLM consulta la knowledge base del cliente
    ↓
LLM llama: get_process_step_schema()          ← conoce el formato
    ↓
LLM extrae pasos del proceso de la KB
    ↓
LLM llama: generate_haccp_analysis(
    product_name="Jamón cocido rebanado",
    process_steps_json="[...]",
    focus_areas="Listeria, Salmonella",
    fda_product_keyword="cooked ham"
)
    ↓
Servidor consulta openFDA → detecta peligros
    ↓
Genera tabla HACCP + guarda Excel
    ↓
Retorna JSON con análisis completo al usuario

Deploy en Railway

# railway.toml (crear en la raíz)
[build]
  builder = "NIXPACKS"

[deploy]
  startCommand = "python server.py"
  healthcheckPath = "/"

Variables de entorno en Railway:

PORT        = (Railway lo asigna automáticamente)
HOST        = 0.0.0.0
OUTPUT_DIR  = /tmp/vigia_outputs
LOG_LEVEL   = INFO

Notas técnicas

  • Transporte: SSE (Server-Sent Events) — estándar MCP para servidores remotos.
  • openFDA: Se consultan los últimos 5 años de retiros alimentarios. No requiere API key.
  • Excel: Se guarda en OUTPUT_DIR. En Railway, es volátil (/tmp); considera montar un volumen persistente o subir a S3/R2 si necesitas conservar los archivos.
  • PCCs determinados por: temperatura de proceso, nombre de etapa, y peligros confirmados en retiros FDA.
  • Normativas de referencia: NOM-251-SSA1-2009, NOM-213-SSA1-2018, Codex CAC/RCP 1-1969 Rev.4.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured