Skip to main content
Glama
Sign In
enesjakozh
Unstructured Document Processor MCP

Unstructured Document Processor MCP

by MKhalusova
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

非構造化文書処理機能を提供するモデルコンテキストプロトコルサーバー。このサーバーにより、LLMは非構造化文書からコンテンツを抽出して利用できるようになります。

このリポジトリは現在作業中ですので、注意して進めてください :)

サポートされているファイルの種類:

{".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"}

前提条件: 次のものが必要です:

この MCP を Claude デスクトップに追加する方法についての簡単な要約:

  1. リポジトリをクローンし、UV 環境をセットアップします。

  2. ルート ディレクトリに.envファイルを作成し、次の環境変数を追加します: UNSTRUCTURED_API_KEY 。

  3. MCP サーバーを実行します: uv run doc_processor.py

  4. ~/Library/Application Support/Claude/に移動し、 claude_desktop_config.jsonを作成します。そのファイルに以下を追加します。

{
    "mcpServers": {
        "unstructured_doc_processor": {
            "command": "PATH/TO/YOUR/UV",
            "args": [
                "--directory",
                "ABSOLUTE/PATH/TO/YOUR/unstructured-mcp/",
                "run",
                "doc_processor.py"
            ],
            "disabled": false
        }
    }
}

  1. Claude Desktopを再起動してください。これでMCPが使用できるようになります。

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…

    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    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

    Resources

    Related MCP Connectors

    Related MCP Servers

    • MarkItDown MCP Server

      canlgz
      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

    • FS-MCP Server

      boleyn
      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

    • fathom-mcp

      RomanShnurov
      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

    Appeared in Searches