Skip to main content
Glama
enesjakozh
NvkAnirudh

LinkedIn Post Generator

by NvkAnirudh
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Generador de publicaciones de LinkedIn

insignia de herrería

Un servidor de Protocolo de Contexto de Modelo (MCP) que automatiza la generación de borradores profesionales de publicaciones de LinkedIn a partir de videos de YouTube. Esta herramienta optimiza la reutilización de contenido extrayendo transcripciones de videos de YouTube, resumiendo el contenido y generando publicaciones atractivas de LinkedIn adaptadas a tus preferencias.

Tabla de contenido

Related MCP server: YouTube Translate MCP

Características

  • Extracción de transcripciones de YouTube : extrae automáticamente las transcripciones de cualquier video de YouTube

  • Resumen de contenido : genere resúmenes concisos con tono personalizable y público objetivo.

  • Generación de publicaciones en LinkedIn : crea publicaciones profesionales en LinkedIn con un estilo y un tono personalizables

  • Flujo de trabajo todo en uno : pase de la URL de YouTube a la publicación de LinkedIn en una sola operación

  • Opciones de personalización : ajuste el tono, la audiencia, el número de palabras y más para que coincida con su marca personal.

  • Integración con MCP : funciona a la perfección con asistentes de IA que admiten el Protocolo de contexto de modelo

Instalación

Desarrollo local

  1. Clonar el repositorio:

    git clone https://github.com/NvkAnirudh/LinkedIn-Post-Generator.git
cd LinkedIn-Post-Generator

  2. Instalar dependencias:

    npm install

  3. Cree un archivo .env basado en el ejemplo:

    cp .env.example .env

  4. Agregue sus claves API al archivo .env :

    OPENAI_API_KEY=your_openai_api_key
YOUTUBE_API_KEY=your_youtube_api_key

  5. Ejecutar el servidor:

    npm run dev

  6. Prueba con MCP Inspector:

    npm run inspect

Uso con Claude Desktop

Este servidor MCP está diseñado para funcionar con Claude Desktop y otros asistentes de IA compatibles con el Protocolo de Contexto de Modelo. Para usarlo con Claude Desktop:

  1. Configure Claude Desktop editando el archivo de configuración en ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) o %APPDATA%\Claude\claude_desktop_config.json (Windows):

    {
  "mcpServers": {
    "linkedin-post-generator": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "@NvkAnirudh/linkedin-post-generator",
        "--key",
        "YOUR_SMITHERY_API_KEY",
        "--config",
        "{\"OPENAI_API_KEY\":\"YOUR_OPENAI_API_KEY\",\"YOUTUBE_API_KEY\":\"YOUR_YOUTUBE_API_KEY\"}",
        "--transport",
        "stdio"
      ]
    }
  }
}

    Reemplazar:

    • YOUR_SMITHERY_API_KEY con su clave API de Smithery

    • YOUR_OPENAI_API_KEY con su clave API de OpenAI

    • YOUR_YOUTUBE_API_KEY con tu clave API de YouTube (opcional)

  2. Reiniciar Claude Desktop

  3. En Claude Desktop, ahora puedes acceder a las herramientas del generador de publicaciones de LinkedIn sin necesidad de volver a configurar las claves API.

Configuración

La aplicación requiere claves API para funcionar correctamente:

  1. Clave API de OpenAI (obligatoria): se utiliza para resumir contenido y generar publicaciones.

  2. Clave API de YouTube (opcional): mejora la recuperación de metadatos de YouTube

Puede proporcionar estas claves de tres maneras:

1. A través de la configuración del escritorio de Claude (recomendado)

Al usar Claude Desktop y Smithery, lo mejor es incluir las claves de API en el archivo de configuración de Claude Desktop, como se muestra en la sección "Uso con Claude Desktop" . De esta forma, las claves se transfieren automáticamente al servidor MCP y no es necesario volver a configurarlas.

2. Como variables de entorno

Al ejecutar localmente, puede configurar claves API como variables de entorno en un archivo .env :

OPENAI_API_KEY=your_openai_api_key
YOUTUBE_API_KEY=your_youtube_api_key

3. Uso de la herramienta Establecer claves API

Si no ha proporcionado claves API a través de la configuración o las variables de entorno, puede configurarlas directamente a través de la interfaz MCP usando la herramienta set_api_keys .

Uso

Herramientas disponibles

Establecer claves API

  • Herramienta: set_api_keys

  • Propósito: Configurar sus claves API

  • Parámetros:

    • openaiApiKey : Su clave API de OpenAI (obligatoria)

    • youtubeApiKey : Tu clave API de YouTube (opcional)

Comprobar claves API

  • Herramienta: check_api_keys

  • Propósito: Verificar el estado de configuración de su clave API

Extraer transcripción

  • Herramienta: extract_transcript

  • Propósito: Obtener la transcripción de un video de YouTube

  • Parámetros:

    • youtubeUrl : URL del vídeo de YouTube

Resumir la transcripción

  • Herramienta: summarize_transcript

  • Propósito: Crear un resumen conciso del contenido del video.

  • Parámetros:

    • transcript : El texto de la transcripción del video

    • tone : educativo, inspirador, profesional o conversacional.

    • audience : general, técnica, empresarial o académica

    • wordCount : Recuento aproximado de palabras para el resumen (100-300)

Generar publicación de LinkedIn

  • Herramienta: generate_linkedin_post

  • Propósito: Crear una publicación de LinkedIn a partir de un resumen

  • Parámetros:

    • summary : Resumen del contenido del vídeo

    • videoTitle : Título del vídeo de YouTube

    • speakerName : Nombre del orador (opcional)

    • hashtags : hashtags relevantes (opcional)

    • tone : Primera persona, tercera persona o líder de pensamiento.

    • includeCallToAction : si se debe incluir una llamada a la acción

Todo en uno: Publicación de YouTube a LinkedIn

  • Herramienta: youtube_to_linkedin_post

  • Propósito: Flujo de trabajo completo desde la URL de YouTube hasta la publicación de LinkedIn

  • Parámetros:

    • youtubeUrl : URL del vídeo de YouTube

    • tone : Tono deseado para la publicación

    • Más opciones de personalización adicionales

Ejemplo de flujo de trabajo

  1. Configure sus claves API usando la herramienta set_api_keys

  2. Utilice la herramienta youtube_to_linkedin_post con una URL de YouTube

  3. Reciba un borrador completo de publicación de LinkedIn listo para publicar

Despliegue

Este servidor se implementa en Smithery , una plataforma para alojar y compartir servidores MCP. La configuración de implementación se define en el archivo smithery.yaml .

Para implementar su propia instancia:

  1. Crea una cuenta en Smithery

  2. Instalar la CLI de Smithery:

    npm install -g @smithery/cli

  3. Implementar el servidor:

    smithery deploy

Contribuyendo

¡Agradecemos tus contribuciones! Aquí te explicamos cómo puedes contribuir al generador de publicaciones de LinkedIn:

Informes de problemas

  • Utilice el rastreador de problemas de GitHub para informar errores o sugerir funciones

  • Proporcione información detallada sobre el problema, incluidos los pasos para reproducirlo, el comportamiento esperado y el comportamiento real.

  • Incluya los detalles de su entorno (sistema operativo, versión de Node.js, etc.) al informar errores

Solicitudes de extracción

  1. Bifurcar el repositorio

  2. Crea una nueva rama ( git checkout -b feature/your-feature-name )

  3. Realiza tus cambios

  4. Ejecute pruebas para asegurarse de que sus cambios no alteren la funcionalidad existente

  5. Confirme sus cambios ( git commit -m 'Add some feature' )

  6. Empujar a la rama ( git push origin feature/your-feature-name )

  7. Abrir una solicitud de extracción

Directrices de desarrollo

  • Siga el estilo y las convenciones del código existente

  • Escribe código claro y comentado

  • Incluir pruebas para nuevas funciones

  • Actualice la documentación para reflejar sus cambios

Sugerencias de funciones

Si tiene ideas para nuevas funciones o mejoras:

  1. Verifique los problemas existentes para ver si su sugerencia ya ha sido propuesta

  2. En caso contrario, abra un nuevo problema con la etiqueta "mejora".

  3. Describa claramente la característica y sus beneficios potenciales.

Documentación

Las mejoras en la documentación siempre son bienvenidas:

  • Corregir errores tipográficos o aclarar la documentación existente

  • Agregar ejemplos o casos de uso

  • Mejorar la estructura u organización de la documentación

Al contribuir a este proyecto, usted acepta que sus contribuciones estarán licenciadas bajo la Licencia MIT del proyecto.

Licencia

Instituto Tecnológico de Massachusetts (MIT)

Available Tools

6 tools
check_api_keysD
ParametersJSON Schema
NameRequiredDescriptionDefault

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.

extract_transcriptD
ParametersJSON Schema
NameRequiredDescriptionDefault
youtubeUrlYesYouTube video URL

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.

generate_linkedin_postD
ParametersJSON Schema
NameRequiredDescriptionDefault
summaryYesSummary of the video content
videoTitleYesTitle of the YouTube video
speakerNameNoName of the speaker in the video (optional)
hashtagsNoRelevant hashtags (optional)
toneNoTone of the LinkedIn postfirst-person
includeCallToActionNoWhether to include a call to action

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.

set_api_keysD
ParametersJSON Schema
NameRequiredDescriptionDefault
openaiApiKeyYesYour OpenAI API key
youtubeApiKeyNoYour YouTube API key (optional)

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.

summarize_transcriptD
ParametersJSON Schema
NameRequiredDescriptionDefault
transcriptYesVideo transcript text
toneNoTone of the summaryprofessional
audienceNoTarget audience for the summarygeneral
wordCountNoApproximate word count for the summary

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.

youtube_to_linkedin_postD
ParametersJSON Schema
NameRequiredDescriptionDefault
youtubeUrlYesYouTube video URL
toneNoTone of the LinkedIn postfirst-person
summaryToneNoTone of the summaryprofessional
audienceNoTarget audiencegeneral
hashtagsNoRelevant hashtags (optional)
includeCallToActionNoWhether to include a call to action

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.

  1. 1 tool updatev1.0.0
    • Changedcheck_api_keys1 field changed
      • removedInput schema / additionalProperties
        Removed value: -false
  2. 6 tool updates
    • First observedcheck_api_keys
    • First observedextract_transcript
    • First observedgenerate_linkedin_post
    • First observedset_api_keys
    • First observedsummarize_transcript
    • First observedyoutube_to_linkedin_post
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

D1.9/5.0

Scored across 6 tools

Disambiguation4/5

Most tools have distinct purposes: checking/setting API keys, extracting/summarizing transcripts, generating posts, and a combined YouTube-to-post workflow. However, 'generate_linkedin_post' and 'youtube_to_linkedin_post' could cause some confusion about when to use each, as the latter might implicitly include extraction and summarization steps.

Naming Consistency4/5

Tool names follow a consistent snake_case pattern with clear verb-action structures (e.g., 'check_api_keys', 'extract_transcript'). The only minor deviation is 'youtube_to_linkedin_post', which uses a 'source_to_destination' format instead of a verb-noun style, but it remains readable and fits the overall convention.

Tool Count5/5

With 6 tools, this server is well-scoped for its purpose of generating LinkedIn posts from various inputs. Each tool appears to serve a specific function in the workflow, from API management to content processing and post generation, without being overly sparse or bloated.

Completeness3/5

The toolset covers key steps like API setup, content extraction, summarization, and post generation, but there are notable gaps. For example, there's no tool for editing or updating existing posts, managing drafts, or handling post scheduling, which could limit agent workflows in a complete LinkedIn posting lifecycle.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches