de en es ja ko ru zh

Python MCP Server Template

Name: Python MCP Server Template
Author: nictuku

by nictuku

Overview Schema Source Related Servers Discussions Admin

Python

plantilla de servidor py-mcp

Este repositorio es una plantilla que te ayuda a crear tus propios servidores MCP (Protocolo de Contexto de Modelo) en Python. Bifurca este repositorio para empezar.

Configuración con uv

Este proyecto utiliza uv para el empaquetado de Python y la gestión de entornos virtuales. Si no tiene uv instalado, consulte la guía oficial de instalación de uv .

Clona tu repositorio bifurcado:

git clone https://github.com/YOUR_USERNAME/YOUR_REPOSITORY_NAME.git
cd YOUR_REPOSITORY_NAME

Cree y active el entorno virtual: uv normalmente crea un directorio .venv en la raíz del proyecto.
```
uv venv
source .venv/bin/activate  # On macOS/Linux
# .venv\Scripts\activate   # On Windows
```
Instalar dependencias: este proyecto utiliza pyproject.toml para administrar las dependencias.
```
uv pip install .
```
Si agrega nuevas dependencias, defínalas en su archivo pyproject.toml y vuelva a ejecutar este comando. Si utiliza un archivo requirements.txt por algún motivo, puede instalarlo con uv pip install -r requirements.txt .

Related MCP server: mcp-framework-starter

Ejecución del servidor

El script mcp_server.py inicia el servidor MCP.

Para ejecutar el servidor directamente:

uv run python mcp_server.py

Integración con Claude Desktop o Cursor

Para usar este servidor MCP con una aplicación como Claude Desktop o Cursor, deberá configurarlo en la configuración de la aplicación. La configuración generalmente implica especificar el comando para ejecutar el servidor.

Aquí tienes un ejemplo de fragmento de configuración. Deberás reemplazar /ABSOLUTE/PATH/TO/PARENT/FOLDER/YOUR_REPOSITORY_NAME por la ruta absoluta real al directorio de tu proyecto en el sistema.

{
    "mcpServers": {
        "my-custom-python-server": {
            "command": "uv",
            "args": [
                "run",
                "--python",
                "/ABSOLUTE/PATH/TO/PARENT/FOLDER/YOUR_REPOSITORY_NAME/.venv/bin/python",
                "/ABSOLUTE/PATH/TO/PARENT/FOLDER/YOUR_REPOSITORY_NAME/mcp_server.py"
            ],
            "workingDirectory": "/ABSOLUTE/PATH/TO/PARENT/FOLDER/YOUR_REPOSITORY_NAME"
        }
    }
}

Explicación de la configuración:

"my-custom-python-server" : este es el nombre que le da a la configuración de su servidor.
"command": "uv" : especifica uv como el comando a ejecutar.
"args" : una lista de argumentos para el comando uv :
- "run" : le indica uv que ejecute un comando dentro de su entorno administrado.
- "--python" : Especifica el intérprete de Python que se usará. Es importante apuntar esto al intérprete de Python dentro de su entorno virtual uv ( .venv/bin/python ).
- "/ABSOLUTE/PATH/TO/PARENT/FOLDER/YOUR_REPOSITORY_NAME/mcp_server.py" : La ruta absoluta a su script de servidor.
"workingDirectory" : especifica el directorio de trabajo para el proceso del servidor, que debe ser el directorio raíz de su proyecto.

Importante:

Asegúrese de que las rutas en args y workingDirectory sean correctas para su sistema.
Si la aplicación no puede localizar uv , podrías tener que especificar su ruta completa en el campo "command" . Normalmente, puedes encontrar esta ruta ejecutando which uv en tu terminal en macOS o Linux, o where uv en Windows.
El servidor escucha en stdio de manera predeterminada, tal como está configurado en mcp_server.py ( mcp.run(transport='stdio') ), que es normalmente lo que esperan aplicaciones como Cursor.

Después de la configuración, la aplicación debería poder comunicarse con su servidor Python MCP.

Available Tools

3 tools

get_jokeD

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_pingD

ParametersJSON Schema

Name	Required	Description	Default
`message`	Yes

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_weatherD

ParametersJSON Schema

Name	Required	Description	Default
`city`	Yes

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

3 tool updatesAug 18, 2025
- First observedget_joke
- First observedget_ping
- First observedget_weather

Deploy Server

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

TDQS

D1.8/5.0

Scored 2026-04-18 10:06 across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: get_joke retrieves jokes, get_ping checks server status, and get_weather fetches weather data. There is no overlap in functionality, making it easy for an agent to select the correct tool without confusion.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with 'get_' as the prefix, using snake_case throughout. This predictable naming scheme enhances readability and usability for agents.

Tool Count3/5

With only 3 tools, the server feels thin for a general-purpose template, as it lacks depth in any specific domain. While the count is not extreme, it may be insufficient for complex workflows, though it's reasonable for a basic example.

Completeness2/5

The tool set is severely incomplete for a Python MCP server template, as it only includes three unrelated, trivial functions without covering any meaningful domain or lifecycle operations. There are significant gaps that would hinder agent performance in practical scenarios.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

hithereiamaliff-mcp-nextcloudOAuth
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Cloud Storage File Systems Workplace & Productivity
238
mcp COAuth
com.wix
A Model Context Protocol server for Wix AI tools
Developer Tools Content Management Systems App Automation
215
anirbanbasu-pymcpOAuth
ai.smithery
Primarily to be used as a template repository for developing MCP servers with FastMCP in Python, P…
Developer Tools
28
Apideck MCP A
dev.apideck.mcp
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Developer Tools
42

Related MCP Servers

MCP Server Template
Developer Tools Agent Orchestration App Automation
hypermodel-labs
A
license
C
quality
D
maintenance
A starter template for building Model Context Protocol servers that can be integrated with Cursor or Claude Desktop, allowing developers to create custom tools and extensions for AI assistants.
Updated a year ago (2025-05-04 22:47 UTC)
1
10 npm
14
MIT
mcp-framework-starter
Developer Tools App Automation
QuantGeekDev
F
license
Not graded
quality
D
maintenance
A starter template for building Model Context Protocol (MCP) servers, enabling developers to create and add custom tools that can be integrated with Claude Desktop.
Updated 2 years ago (2025-04-01 01:26 UTC)
2
-
MCP Server Boilerplate
CaptainCrouton89
F
license
C
quality
D
maintenance
A starter template for building Model Context Protocol servers that integrate with AI assistants like Claude and Cursor, providing custom tools, resource providers, and prompt templates.
Updated a year ago (2025-07-21 00:05 UTC)
2
5 npm
-
MCP Server Boilerplate
CaptainCrouton89
F
license
C
quality
D
maintenance
A starter template for building Model Context Protocol servers that integrate with AI assistants like Claude and Cursor, providing custom tools, resource providers, and prompt templates.
Updated a year ago (2025-07-21 01:49 UTC)
2
5 npm
-