Skip to main content
Glama

mcp-pandoc: un servidor MCP de conversión de documentos

Incluido oficialmente en el proyecto de código abierto de servidores de Protocolo de Contexto de Modelo . 🎉

Descripción general

Un servidor de Protocolo de Contexto de Modelo para la conversión de formatos de documentos mediante pandoc . Este servidor proporciona herramientas para transformar contenido entre diferentes formatos de documentos, conservando el formato y la estructura.

Tenga en cuenta que mcp-pandoc se encuentra actualmente en desarrollo inicial. La compatibilidad con PDF también está en desarrollo, y la funcionalidad y las herramientas disponibles están sujetas a cambios y ampliaciones a medida que mejoramos el servidor.

Crédito: Este proyecto utiliza el paquete Python Pandoc para la conversión de documentos, lo que constituye la base de este proyecto.

Related MCP server: md2pdf-mcp

Manifestación

mcp-pandoc - v1: Conversión fluida de formatos de documentos para Claude mediante el servidor MCP

🎥 Míralo en YouTube

Más por venir...

Herramientas

  1. convert-contents

    • Transforma el contenido entre formatos compatibles

    • Entradas:

      • contents (cadena): contenido de origen a convertir (obligatorio si no se proporciona input_file)

      • input_file (cadena): ruta completa al archivo de entrada (obligatorio si no se proporciona el contenido)

      • input_format (cadena): formato de origen del contenido (predeterminado en Markdown)

      • output_format (cadena): formato de destino (predeterminado en Markdown)

      • output_file (cadena): ruta completa para el archivo de salida (obligatorio para los formatos pdf, docx, rst, latex, epub)

    • Formatos de entrada/salida admitidos:

      • reducción

      • html

      • pdf

      • docx

      • primero

      • látex

      • libro electrónico

      • TXT

    • Nota: Para formatos avanzados (pdf, docx, rst, latex, epub), se requiere una ruta de archivo de salida

Formatos compatibles

Formatos admitidos actualmente:

Formatos básicos (conversión directa):

  • Texto sin formato (.txt)

  • Markdown (.md)

  • HTML (.html)

Formatos avanzados (requiere rutas de archivo completas):

  • PDF (.pdf) - requiere instalación de TeX Live

  • DOCX (.docx)

  • RST (.rst)

  • LaTeX (.tex)

  • EPUB (.epub)

Nota: Para formatos avanzados:

  1. Se requieren rutas de archivo completas con nombre de archivo y extensión

  2. La conversión de PDF requiere la instalación de TeX Live (consulte la sección Requisitos críticos -> Para macOS: brew install texlive )

  3. Cuando no se especifica ninguna ruta de salida:

    • Formatos básicos: Muestra el contenido convertido en el chat.

    • Formatos avanzados: Se puede guardar en el directorio temporal del sistema (/tmp/ en sistemas Unix)

Uso y configuración

Para utilizar el publicado

{
  "mcpServers": {
    "mcp-pandoc": {
      "command": "uvx",
      "args": ["mcp-pandoc"]
    }
  }
}

⚠️ Notas importantes

Requisitos críticos

  1. Requisitos previos para la conversión de PDF

    • TeX Live debe estar instalado antes de intentar la conversión a PDF

    • Comandos de instalación:

      # Ubuntu/Debian
      sudo apt-get install texlive-xetex
      
      # macOS
      brew install texlive
      
      # Windows
      # Install MiKTeX or TeX Live from:
      # https://miktex.org/ or https://tug.org/texlive/
  2. Requisitos de ruta de archivo

    • Al guardar o convertir archivos, DEBE proporcionar las rutas de archivo completas, incluido el nombre del archivo y la extensión.

    • La herramienta no genera automáticamente nombres de archivos ni extensiones.

Ejemplos

✅ Uso correcto:

# Converting content to PDF
"Convert this text to PDF and save as /path/to/document.pdf"

# Converting between file formats
"Convert /path/to/input.md to PDF and save as /path/to/output.pdf"

❌ Uso incorrecto:

# Missing filename and extension
"Save this as PDF in /documents/"

# Missing complete path
"Convert this to PDF"

# Missing extension
"Save as /documents/story"

Problemas comunes y soluciones

  1. La conversión de PDF falla

    • Error: "xelatex no encontrado"

    • Solución: Instale primero TeX Live (consulte los comandos de instalación anteriores)

  2. La conversión de archivos falla

    • Error: "Ruta de archivo no válida"

    • Solución: proporcione la ruta completa, incluido el nombre del archivo y la extensión

    • Ejemplo: /path/to/document.pdf en lugar de simplemente /path/to/

  3. La conversión de formato falla

    • Error: "Formato no compatible"

    • Solución: utilice únicamente formatos compatibles:

      • Básico: txt, html, markdown

      • Avanzado: pdf, docx, rst, latex, epub

Inicio rápido

Instalar

Opción 1: Instalación manual mediante el archivo de configuración claude_desktop_config.json

  • En MacOS: open ~/Library/Application\ Support/Claude/claude_desktop_config.json

  • En Windows: %APPDATA%/Claude/claude_desktop_config.json

ℹ️ Reemplace con la ruta de su proyecto clonado localmente

"mcpServers": {
  "mcp-pandoc": {
    "command": "uv",
    "args": [
      "--directory",
      "<DIRECTORY>/mcp-pandoc",
      "run",
      "mcp-pandoc"
    ]
  }
}
"mcpServers": {
  "mcp-pandoc": {
    "command": "uvx",
    "args": [
      "mcp-pandoc"
    ]
  }
}

Opción 2: Instalar automáticamente la configuración de servidores publicados a través de Smithery

Ejecute el siguiente comando bash para instalar automáticamente mcp-pandoc pypi publicado para Claude Desktop a través de Smithery :

npx -y @smithery/cli install mcp-pandoc --client claude

Nota : Para utilizar mcp-pandoc configurado localmente, siga el paso "Configuración de servidores no publicados/desarrollo" anterior.

Desarrollo

Construcción y publicación

Para preparar el paquete para su distribución:

  1. Sincronizar dependencias y actualizar archivo de bloqueo:

uv sync
  1. Distribuciones de paquetes de compilación:

uv build

Esto creará distribuciones de origen y de rueda en el directorio dist/ .

  1. Publicar en PyPI:

uv publish

Nota: Deberás configurar las credenciales de PyPI a través de variables de entorno o indicadores de comando:

  • Token: --token o UV_PUBLISH_TOKEN

  • O nombre de usuario/contraseña: --username / UV_PUBLISH_USERNAME y --password / UV_PUBLISH_PASSWORD

Depuración

Dado que los servidores MCP se ejecutan en stdio, la depuración puede ser complicada. Para una experiencia óptima, recomendamos usar el Inspector MCP .

Puede iniciar el Inspector MCP a través de npm con este comando:

npx @modelcontextprotocol/inspector uv --directory /Users/vivekvells/Desktop/code/ai/mcp-pandoc run mcp-pandoc

Al iniciarse, el Inspector mostrará una URL a la que podrá acceder en su navegador para comenzar a depurar.


Contribuyendo

Agradecemos sus contribuciones para mejorar mcp-pandoc. Así es como puede participar:

  1. Reportar problemas : ¿Encontraste un error o tienes alguna solicitud de funcionalidad? Abre un problema en nuestra página de problemas de GitHub .

  2. Enviar solicitudes de extracción : mejore la base de código o agregue funciones mediante la creación de una solicitud de extracción.


Available Tools

1 tool
convert-contentsA

Converts content between different formats. Transforms input content from any supported format into the specified output format.

🚨 CRITICAL REQUIREMENTS - PLEASE READ:

  1. PDF Conversion:

    • You MUST install TeX Live BEFORE attempting PDF conversion:

    • Ubuntu/Debian: sudo apt-get install texlive-xetex

    • macOS: brew install texlive

    • Windows: Install MiKTeX or TeX Live from https://miktex.org/ or https://tug.org/texlive/

    • PDF conversion will FAIL without this installation

  2. File Paths - EXPLICIT REQUIREMENTS:

    • When asked to save or convert to a file, you MUST provide:

      • Complete directory path

      • Filename

      • File extension

    • Example request: 'Write a story and save as PDF'

    • You MUST specify: '/path/to/story.pdf' or 'C:\Documents\story.pdf'

    • The tool will NOT automatically generate filenames or extensions

  3. File Location After Conversion:

    • After successful conversion, the tool will display the exact path where the file is saved

    • Look for message: 'Content successfully converted and saved to: [file_path]'

    • You can find your converted file at the specified location

    • If no path is specified, files may be saved in system temp directory (/tmp/ on Unix systems)

    • For better control, always provide explicit output file paths

Supported formats:

  • Basic (returned inline): txt, html, markdown, ipynb

  • Advanced (REQUIRE complete file paths): pdf, docx, rst, latex, epub, odt, pptx

  • pptx is WRITE-ONLY: it can be produced, but not used as an input format ✅ CORRECT Usage Examples:

  1. 'Convert this text to HTML' (basic conversion)

    • Tool will show converted content

  2. 'Save this text as PDF at /documents/story.pdf'

    • Correct: specifies path + filename + extension

    • Tool will show: 'Content successfully converted and saved to: /documents/story.pdf'

❌ INCORRECT Usage Examples:

  1. 'Save this as PDF in /documents/'

    • Missing filename and extension

  2. 'Convert to PDF'

    • Missing complete file path

When requesting conversion, ALWAYS specify:

  1. The content or input file

  2. The desired output format

  3. For advanced formats: complete output path + filename + extension Example: 'Convert this markdown to PDF and save as /path/to/output.pdf'

🎨 DOCX, ODT & PPTX STYLING: 4. Custom Styling with Reference Documents:

  • Use reference_doc parameter to apply professional styling to DOCX, ODT and PPTX output

  • The reference document MUST match the output format: .docx for docx, .odt for odt, .pptx for pptx

  • Create custom templates with your branding, fonts, and formatting

  • Perfect for corporate reports, academic papers, and professional documents

  • Example: 'Convert this report to DOCX using /templates/corporate-style.docx as reference and save as /reports/Q4-report.docx'

🎯 PANDOC FILTERS (NEW FEATURE): 5. Pandoc Filter Support:

  • Use filters parameter to apply custom Pandoc filters during conversion

  • Filters are Python scripts that modify document content during processing

  • Perfect for Mermaid diagram conversion, custom styling, and content transformation

  • Example: 'Convert this markdown with mermaid diagrams to DOCX using filters=["./filters/mermaid-to-png-vibrant.py"] and save as /reports/diagram-report.docx'

📋 Creating Reference Documents:

  • Generate template: pandoc -o template.docx --print-default-data-file reference.docx

  • Customize in Word/LibreOffice: fonts, colors, headers, margins

  • Use for consistent branding across all documents

📋 Filter Requirements:

  • Filters must be executable Python scripts

  • Use absolute paths or paths relative to current working directory

  • Filters are applied in the order specified

  • Common filters: mermaid conversion, color processing, table formatting

📄 Defaults File Support (NEW FEATURE): 7. Pandoc Defaults File Support:

  • Use defaults_file parameter to specify a YAML configuration file

  • Similar to using pandoc -d option in the command line

  • Allows setting multiple options in a single file

  • Options in the defaults file can include filters, reference-doc, and other Pandoc options

  • Example: 'Convert this markdown to DOCX using defaults_file="/path/to/defaults.yaml" and save as /reports/report.docx'

Note: After conversion, always check the success message for the exact file location.

ParametersJSON Schema
NameRequiredDescriptionDefault
filtersNoList of Pandoc filter paths to apply during conversion. Filters are applied in the order specified.
contentsNoThe content to be converted (required if input_file not provided)
input_fileNoComplete path to input file including filename and extension (e.g., '/path/to/input.md')
output_fileNoComplete path where to save the output including filename and extension (required for pdf, docx, rst, latex, epub, odt, pptx formats)
input_formatNoSource format of the content (defaults to markdown)markdown
defaults_fileNoPath to a Pandoc defaults file (YAML) containing conversion options. Similar to using pandoc -d option.
output_formatNoDesired output format (defaults to markdown). Note pptx is write-only: it can be produced but not read.markdown
reference_docNoPath to a reference document to use for styling. Supported for docx, odt and pptx output. The file must match the output format: a .docx reference for docx output, .odt for odt, .pptx for pptx.

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does well by explaining that PDF conversion requires TeX Live, that filenames won't be auto-generated, that files may be saved to temp directory if no path is given, and that pptx is write-only. It also mentions the success message that reveals the saved location. The only minor gap is not explicitly stating whether operations are reversible or if any destructive actions occur, but for a conversion tool, this is less critical.

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

Conciseness2/5

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

The description is excessively long and repetitive. Key information about file paths is repeated multiple times (e.g., in the critical requirements, incorrect usage examples, and the final note). The use of emojis, many sections, and multiple examples makes it hard to scan quickly. While it is front-loaded with the main purpose, the sheer volume undermines conciseness.

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

Completeness5/5

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

The description is highly complete given the tool's complexity. It covers all major usage scenarios, including basic conversions, advanced format path requirements, styling with reference documents, Pandoc filters, and defaults files. It even explains output location and success messages, which is valuable since there is no output schema. The description leaves little room for user confusion about how to proceed.

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

Parameters5/5

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

Although the schema already provides descriptions for all 8 parameters, the tool description significantly enriches parameter understanding. It explains the purpose and usage of `reference_doc`, `filters`, `defaults_file`, and clarifies the importance of `output_file` for advanced formats. For example, it gives a specific example for using filters with Mermaid diagrams and explains that reference documents must match output format. This adds substantial value beyond the schema.

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

Purpose4/5

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

The first sentence clearly states the tool's function: 'Converts content between different formats.' This is a specific verb+resource description that distinguishes it from potential alternative tools. The rest of the description reinforces this with supported formats and examples. However, the purpose is somewhat diluted by the extensive additional requirements and feature explanations.

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

Usage Guidelines5/5

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

The description provides explicit, actionable guidance on when and how to use the tool, including correct and incorrect usage examples, requirements for PDF conversion, and file path specifications. It clearly delineates basic vs. advanced formats and instructs users to always specify content, output format, and complete file paths for advanced formats. This goes beyond mere context to offer concrete usage rules.

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 updatev0.11.1
    • Changedconvert-contents4 fields changed
      • changedInput schema / properties / output_file / description
        Previous value: -"Complete path where to save the output including filename and extension (required for pdf, docx, rst, latex, epub formats)"New value: +"Complete path where to save the output including filename and extension (required for pdf, docx, rst, latex, epub, odt, pptx formats)"
      • changedInput schema / properties / output_format / description
        Previous value: -"Desired output format (defaults to markdown)"New value: +"Desired output format (defaults to markdown). Note pptx is write-only: it can be produced but not read."
      • changedInput schema / properties / output_format / enum
        Previous value: -[
        -  "markdown",
        -  "html",
        -  "pdf",
        -  "docx",
        -  "rst",
        -  "latex",
        -  "epub",
        -  "txt",
        -  "ipynb",
        -  "odt"
        -]New value: +[
        +  "markdown",
        +  "html",
        +  "pdf",
        +  "docx",
        +  "rst",
        +  "latex",
        +  "epub",
        +  "txt",
        +  "ipynb",
        +  "odt",
        +  "pptx"
        +]
      • changedInput schema / properties / reference_doc / description
        Previous value: -"Path to a reference document to use for styling (supported for docx output format)"New value: +"Path to a reference document to use for styling. Supported for docx, odt and pptx output. The file must match the output format: a .docx reference for docx output, .odt for odt, .pptx for pptx."
  2. 1 tool updatev0.8.1
    • Changedconvert-contents3 fields changed
      • addedInput schema / additionalProperties
        Added value: +false
      • removedInput schema / allOf
        Removed value: -[
        -  {
        -    "if": {
        -      "properties": {
        -        "output_format": {
        -          "enum": [
        -            "pdf",
        -            "docx",
        -            "rst",
        -            "latex",
        -            "epub"
        -          ]
        -        }
        -      }
        -    },
        -    "then": {
        -      "required": [
        -        "output_file"
        -      ]
        -    }
        -  }
        -]
      • removedInput schema / oneOf
        Removed value: -[
        -  {
        -    "required": [
        -      "contents"
        -    ]
        -  },
        -  {
        -    "required": [
        -      "input_file"
        -    ]
        -  }
        -]
  3. 1 tool updatev1.0.0
    • First observedconvert-contents

TDQS

A4.4/5.0

Scored across 1 tool

Disambiguation5/5

There is only one tool, so there is no possibility of an agent mistaking it for another. Its purpose is clearly defined as content conversion, with no overlapping tools.

Naming Consistency5/5

Although there is only one tool, the name 'convert-contents' follows a clear verb_noun convention and is semantically appropriate. With no other tools, there are no naming conflicts or mixed conventions.

Tool Count3/5

A single tool for Pandoc conversion feels minimal, though it can cover many conversions through its parameters. It is on the thin side of the acceptable range for a focused converter server.

Completeness5/5

The tool supports conversion across a wide range of formats, including inline returns and file outputs, plus advanced options like reference documents, filters, and defaults files. For a conversion-only server, this covers the domain thoroughly with no obvious operational gaps.

Maintenance

ActivitySlowing
ResponsivenessWithin a week

Related MCP Connectors

Related MCP Servers