de en es ja ko ru zh

Unit Converter MCP Server

Name: Unit Converter MCP Server
Author: Robbo-lab

by Robbo-lab

Overview Schema Source Related Servers Discussions Admin

Python

Local

Tutorial de API + MCP de Conversor de Unidades

construye la aplicación FastAPI, la envuelve con FastMCP, monta los endpoints HTTP/SSE de MCP, registra recursos y prompts, e inicia uvicorn.
requirements.txt – Dependencias de Python.

Requisitos previos

Python 3.10+ (probado con 3.12).
Entorno virtual.
Inspector de npm a continuación.

⸻

Related MCP server: Local Utilities MCP Server

Configuración desde esta carpeta

python -m venv .venv

# Mac or Gitbash
source .venv/bin/activate

# Windows powershell:
.venv\Scripts\activate
python -m pip install -r requirements.txt

⸻

Ejecutar el servidor HTTP + MCP

# start the server
python converter_streamable_http_server.py

# or
python -m converter_streamable_http_server

Verás:

Swagger UI: http://localhost:8003/docs
ReDoc: http://localhost:8003/redoc

Endpoints MCP servidos por FastMCP:

streamable-http: http://localhost:8003/mcp
SSE: http://localhost:8003/sse

⸻

Probar los endpoints HTTP (curl)

curl -X POST "http://localhost:8003/miles-to-kilometers?miles=3.1" \
 -H "Authorization: Bearer 143f4a46d74fee0d7918b2857577868cb3daf9e6e50ee91c2f7975ba26fdb8f7"

# If we use pydantic models
curl -X POST "http://localhost:8003/miles-to-kilometers" \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer Y658139cf61948208ed76a4b36122b9552ec5c3f6da5e02f7c5d85d995dede17dE" \
 -d "3.1"

# Celsius → Fahrenheit
curl -X POST "http://localhost:8003/celsius-to-fahrenheit" \
 -H "Content-Type: application/json" \
 -d "25"

# Fahrenheit → Celsius
curl -X POST "http://localhost:8003/fahrenheit-to-celsius" \
 -H "Content-Type: application/json" \
 -d "86"

# Kilometers → Miles
curl -X POST "http://localhost:8003/kilometers-to-miles" \
 -H "Content-Type: application/json" \
 -d "5"

# Miles → Kilometers (rejects negative values)
curl -X POST "http://localhost:8003/miles-to-kilometers" \
 -H "Content-Type: application/json" \
 -d "3.1"

Cada endpoint devuelve un JSON como:

{ "result": <número>, "operation": "..." } o { "error": "..." } para entradas no válidas.

Cabeceras y Autenticación (común a todos)

Añadir tipo de contenido JSON (y opcionalmente tu token de autenticación)

-H "Content-Type: application/json"
-H "Authorization: Bearer "

Nuestro servidor aún no requiere autenticación, podemos omitir la cabecera Authorization.

Uso con MCP (Ejemplo de VS Code)

Inicia el servidor como se indicó anteriormente.
Apunta tu cliente MCP al proceso.

// Example VS Code .vscode/mcp.json entry:
{
  "servers": {
    "UnitConverter": {
      "command": "python",
      "args": ["converter_api_tutorial.py"]
    }
  }
}

Desde el cliente MCP, lista los artefactos. Deberías ver:
- Herramientas: celsius_to_fahrenheit, fahrenheit_to_celsius, kilometers_to_miles, miles_to_kilometers
- Recursos: resource://unit_reference, resource://troubleshooting_guide
- Prompts: explain_conversion, api_usage

⸻

Inspeccionar con el Inspector MCP de npm

explora todo (herramientas, recursos, prompts) en un navegador.
con el servidor ya ejecutándose en http://localhost:8003

# If env error appears
npx @modelcontextprotocol/inspector@latest -e DUMMY=1 --url http://localhost:8003/mcp --transport streamable-http

# If you want to test the older HTTP:
npx @modelcontextprotocol/inspector@latest -e DUMMY=1 --url http://localhost:8003/mcp --transport http

# If you want to test the deprecated SSE:
npx @modelcontextprotocol/inspector@latest -e DUMMY=1 --url http://localhost:8003/sse --transport sse

Para ejecutar solo el servidor STDIO

# If venv is ".venv", change to .\.venv\Scripts\python.exe
npx @modelcontextprotocol/inspector python converter_stdio_server.py

La interfaz de usuario se ejecuta en localhost:5173 por defecto.
Cambia el puerto de la interfaz si es necesario: CLIENT_PORT=8080 npx @modelcontextprotocol/inspector --url http://localhost:8003/mcp --transport http
Añade cabeceras si es necesario: --header "Authorization: Bearer TOKEN".

Ejemplos de JSON-RPC para Prompts y Recursos

Listar todos los prompts

curl -s -X POST <SERVER_URL> \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"prompts/list","params":{},"id":1}'

⸻

Obtener un prompt específico

curl -s -X POST <SERVER_URL> \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"prompts/get","params":{"name":"summarize"},"id":2}'

⸻

Renderizar/ejecutar un prompt con variables

curl -s -X POST <SERVER_URL> \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"prompts/render","params":{"name":"summarize","variables":{"text":"This is the content to summarize","tone":"neutral"}},"id":3}'

Listar recursos disponibles

curl -s -X POST <SERVER_URL> \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"resources/list","params":{},"id":4}'

Leer un recurso por URI

curl -s -X POST <SERVER_URL> \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"resources/read","params":{"uri":"file:///data/report.pdf"},"id":5}'

Buscar recursos (si es compatible)

curl -s -X POST <SERVER_URL> \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"resources/search","params":{"query":"error OR exception","limit":50},"id":6}'

⸻

Manejo de errores

Error de análisis (-32700)
Solicitud no válida (-32600)
Método no encontrado (-32601)
Parámetros no válidos (-32602)
Error interno (-32603)

Notas

macOS/Linux (bash/zsh) • Los ejemplos anteriores funcionarán tal cual.

# Windows PowerShell
curl -Method POST <SERVER_URL> `  -Headers @{ "Content-Type"="application/json" }`
-Body '{"jsonrpc":"2.0","method":"prompts/list","params":{},"id":1}'

Windows CMD

curl -s -X POST <SERVER_URL> -H "Content-Type: application/json" -d "{\"jsonrpc\":\"2.0\",\"method\":\"prompts/list\",\"params\":{},\"id\":1}"

This server cannot be deployed

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Openweather A
io.github.pipeworx-io
OpenWeather MCP — wraps the OpenWeatherMap API (openweathermap.org)
Weather Services Location Services
2
BakingTab — Baking Conversions for AI A
io.github.zhaoyaqi18
Baking unit conversion (cups/grams/temp/recipe scaling). convert_amount, convert_temperature
Data Platforms
51
Unit & Currency Converter A
io.github.guptaprakhariitr
60+ units, live FX, timezones, and date arithmetic for AI agents.
Finance Location Services
621
Numbers A
io.github.pipeworx-io
Number utilities MCP.
Developer Tools
442

Related MCP Servers

Weather MCP Server
Weather Services
mkowalskizoovu
F
license
Not graded
quality
D
maintenance
Enables temperature conversion from Fahrenheit to Celsius through HTTP requests. Provides a simple MCP tool for temperature unit conversion with AWS Lambda deployment support.
Updated a year ago (2025-10-21 09:08 UTC)
19 npm
-
Local Utilities MCP Server
Developer Tools File Systems
aiforhumans
A
license
Not graded
quality
D
maintenance
Provides essential utility tools for text processing, file operations, hashing, temperature conversion, password generation, and date/time operations through a comprehensive MCP interface.
Updated a year ago (2025-06-25 19:36 UTC)
MIT
mcp-units
Developer Tools
sellisd
A
license
A
quality
D
maintenance
MCP server for converting cooking measurements (volume, weight, temperature) between common units like ml, cup, g, oz, and Celsius/Fahrenheit.
Updated 4 months ago (2026-06-26 17:43 UTC)
3
1
MIT
mcp-units
Developer Tools
quantumleeps
A
license
A
quality
D
maintenance
An MCP server that provides deterministic unit conversions backed by Pint, enabling exact unit conversions, compatibility checks, and parsing of quantities for LLMs.
Updated 8 months ago (2026-02-18 03:16 UTC)
5
MIT