Skip to main content
Glama
Sign In
enesjakozh

Unstructured Document Processor MCP

by MKhalusova
GitHub
Python
2
  • Apple
OverviewInspectNewSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

Integrations

  • Supports processing JPEG/JPG files to extract content for large language models

  • Supports processing Org files to extract content for large language models

  • Supports processing SVG files to extract content for large language models

Un servidor de Protocolo de Contexto de Modelo que proporciona capacidades de procesamiento de documentos no estructurados. Este servidor permite a los LLM extraer y utilizar contenido de un documento no estructurado.

Este repositorio es un trabajo en progreso, proceda con precaución :)

Tipos de archivos admitidos:

{".abw", ".bmp", ".csv", ".cwk", ".dbf", ".dif", ".doc", ".docm", ".docx", ".dot", ".dotm", ".eml", ".epub", ".et", ".eth", ".fods", ".gif", ".heic", ".htm", ".html", ".hwp", ".jpeg", ".jpg", ".md", ".mcw", ".mw", ".odt", ".org", ".p7s", ".pages", ".pbd", ".pdf", ".png", ".pot", ".potm", ".ppt", ".pptm", ".pptx", ".prn", ".rst", ".rtf", ".sdp", ".sgl", ".svg", ".sxg", ".tiff", ".txt", ".tsv", ".uof", ".uos1", ".uos2", ".web", ".webp", ".wk2", ".xls", ".xlsb", ".xlsm", ".xlsx", ".xlw", ".xml", ".zabw"}

Prerrequisitos: Necesitarás:

Resumen rápido sobre cómo agregar este MCP a su Claude Desktop:

  1. Clonar el repositorio y configurar el entorno UV.
  2. Cree un archivo .env en el directorio raíz y agregue la siguiente variable env: UNSTRUCTURED_API_KEY .
  3. Ejecute el servidor MCP: uv run doc_processor.py
  4. Vaya a ~/Library/Application Support/Claude/ y cree un archivo claude_desktop_config.json . En ese archivo, agregue:
{ "mcpServers": { "unstructured_doc_processor": { "command": "PATH/TO/YOUR/UV", "args": [ "--directory", "ABSOLUTE/PATH/TO/YOUR/unstructured-mcp/", "run", "doc_processor.py" ], "disabled": false } } }
  1. Reinicie Claude Desktop. Ahora debería poder usar el MCP.

This server cannot be installed

-
security - not tested
F
license - not found
-
quality - not tested

local-only server

The server can only run on the client's local machine because it depends on local resources.

Un servidor de protocolo de contexto de modelo que permite a los LLM extraer y utilizar contenido de documentos no estructurados en una amplia variedad de formatos de archivos.

Related Resources

Related MCP Servers

  • MCP Word Counter

    qpd-v
    A
    security
    A
    license
    A
    quality
    A Model Context Protocol server that provides tools for analyzing text documents, including counting words and characters. This server helps LLMs perform text analysis tasks by exposing simple document statistics functionality.
    Last updated -
    1
    8
    7
    JavaScript
    Apache 2.0

  • MCP File Context Server

    bsmi021
    -
    security
    A
    license
    -
    quality
    A Model Context Protocol server that enables LLMs to read, search, and analyze code files with advanced caching and real-time file watching capabilities.
    Last updated -
    45
    8
    JavaScript
    MIT License
    • Linux
    • Apple

  • MCP Web Tools Server

    surya-madhav
    -
    security
    A
    license
    -
    quality
    A Model Context Protocol server that allows LLMs to interact with web content through standardized tools, currently supporting web scraping functionality.
    Last updated -
    Python
    MIT License
    • Linux
    • Apple

  • MCP URL Fetcher

    nathanonn
    -
    security
    F
    license
    -
    quality
    A Model Context Protocol server that enables LLMs to fetch and process web content in multiple formats (HTML, JSON, Markdown, text) with automatic format detection.
    Last updated -
    TypeScript
    • Apple

View all related MCP servers

Appeared in Searches

New MCP Servers

ID: 6ncg8w9ovd