Skip to main content
Glama
Unstructured Document Processor MCP

Unstructured Document Processor MCP

by MKhalusova

A Model Context Protocol server that provides unstructured document processing capabilities. This server enables LLMs to extract and use content from an unstructured document.

This repo is work in progress, proceed with caution :)

Supported file types:

{".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"}

Prerequisites: You'll need:

Quick TLDR on how to add this MCP to your Claude Desktop:

  1. Clone the repo and set up the UV environment.

  2. Create a .env file in the root directory and add the following env variable: UNSTRUCTURED_API_KEY.

  3. Run the MCP server: uv run doc_processor.py

  4. Go to ~/Library/Application Support/Claude/ and create a claude_desktop_config.json. In that file add:

{
    "mcpServers": {
        "unstructured_doc_processor": {
            "command": "PATH/TO/YOUR/UV",
            "args": [
                "--directory",
                "ABSOLUTE/PATH/TO/YOUR/unstructured-mcp/",
                "run",
                "doc_processor.py"
            ],
            "disabled": false
        }
    }
}
  1. Restart Claude Desktop. You should now be able to use the MCP.

Available Tools

1 tool
process_documentC
Sends document to process with Unstructured, return the content of the document
 Args:
filepath: path to the document

Inputs: filepath (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or confusion between tools. The single tool has a clear, distinct purpose of processing documents with Unstructured.

    Naming Consistency5/5

    The single tool name 'process_document' follows a clear verb_noun pattern. Since there is only one tool, consistency is inherently perfect with no deviations to evaluate.

    Tool Count2/5

    A single tool is too few for a server named 'Unstructured Document Processor MCP', which suggests broader document processing capabilities. This minimal set feels thin and under-scoped for the apparent domain.

    Completeness2/5

    The tool surface is severely incomplete for document processing. It only provides a basic processing function, lacking essential operations like document listing, metadata retrieval, format conversion, or batch processing, which are typical in such domains.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that converts various file formats (PDF, PowerPoint, Word, Excel, Images, etc.) to Markdown to make them accessible to LLMs.
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that provides intelligent file reading and semantic search capabilities across multiple document formats with security-first access controls.
      7
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that provides AI assistants with direct access to local document collections through full-text search, supporting multiple formats and hierarchical collections.
      MIT