DocMorph Studio
Render Mermaid diagrams, Markdown to PDF and outlines, image OCR, and media metadata cleanup.
使うべきか
品質と安全性
検出事項（4）
- LOWTool 'extract_markdown_outline' description lacks action verbextract_markdown_outline 内
- LOWTool 'parse_pdf_to_markdown' description lacks action verbparse_pdf_to_markdown 内
- LOWTool 'image_ocr_recognize' description lacks action verbimage_ocr_recognize 内
- LOWTool 'sanitize_media_security' description lacks action verbsanitize_media_security 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"docmorph-studio": {
"url": "https://docmorph.dev/mcp/sse"
}
}
}リモートエンドポイント
https://docmorph.dev/mcp/ssessehttps://docmorph.dev/mcpstreamable-httpできること
ツール一覧
ツール（8）
⚪render_mermaid_diagram(syntax, title, theme)
Render a Mermaid diagram into styled SVG vector image code and node metadata. Supports flowchart/graph and sequenceDiagram (sequence) types. Other types (ER/gantt/mindmap/pie/state) should be rendered on client-side using mermaid.js.
入力スキーマ
{
"type": "object",
"properties": {
"syntax": {
"type": "string",
"description": "Mermaid chart syntax (e.g. 'graph TD; A[Start]-->B[End];')"
},
"title": {
"type": "string",
"description": "Optional diagram title"
},
"theme": {
"type": "string",
"enum": [
"default",
"neutral",
"dark",
"forest",
"corporate"
],
"description": "Color palette theme (default: 'default')"
}
},
"required": [
"syntax"
]
}🟢extract_markdown_outline(content, markdown)
Extract hierarchical headings, table of contents, word/character statistics, and document structure outline from Markdown text.
入力スキーマ
{
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "Full Markdown text to analyze"
},
"markdown": {
"type": "string",
"description": "Alternative alias for content property"
}
},
"required": [
"content"
]
}⚪convert_markdown_to_pdf(markdown, title, theme, pageSize)
Compile Markdown text into a styled, publication-ready PDF document with automatic pagination and headers.
入力スキーマ
{
"type": "object",
"properties": {
"markdown": {
"type": "string",
"description": "Markdown text to compile"
},
"title": {
"type": "string",
"description": "Document title for the PDF header"
},
"theme": {
"type": "string",
"enum": [
"default",
"neutral",
"dark",
"forest",
"corporate",
"academic",
"modern",
"minimal"
],
"description": "PDF layout and typography theme (default: 'academic')"
},
"pageSize": {
"type": "string",
"enum": [
"A4",
"Letter"
],
"description": "Page size specification (default: 'A4')"
}
},
"required": [
"markdown"
]
}🟢parse_pdf_to_markdown(base64Pdf, fileName)
Extract structured Markdown, tables, and mathematical formulas from a base64 encoded PDF using AI vision OCR.
入力スキーマ
{
"type": "object",
"properties": {
"base64Pdf": {
"type": "string",
"description": "Base64 encoded PDF binary data"
},
"fileName": {
"type": "string",
"description": "Original filename"
}
},
"required": [
"base64Pdf"
]
}🟢image_ocr_recognize(base64Image, language, mode)
Extract multilingual text, complex headings, formulas, and tabular data from images using multimodal AI vision.
入力スキーマ
{
"type": "object",
"properties": {
"base64Image": {
"type": "string",
"description": "Base64 encoded image string or data URL"
},
"language": {
"type": "string",
"description": "Language hint (auto, zh, en, ja, ko, etc.)"
},
"mode": {
"type": "string",
"enum": [
"general",
"table",
"handwriting",
"meme_scene",
"formula"
],
"description": "OCR recognition mode"
}
},
"required": [
"base64Image"
]
}⚪assist_ocr_text(text, action, targetLang)
AI assistant to translate, proofread, or summarize extracted OCR document text.
入力スキーマ
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Extracted text content"
},
"action": {
"type": "string",
"enum": [
"translate",
"proofread",
"summarize"
],
"description": "AI action to perform"
},
"targetLang": {
"type": "string",
"description": "Target language for translation"
}
},
"required": [
"text",
"action"
]
}🟢inspect_media_security(base64Data, mediaType, fileName)
Deeply inspect image, video, or audio files for privacy leaks, including GPS physical coordinates, camera/recorder hardware serials, recording timestamps, and editing software signatures.
入力スキーマ
{
"type": "object",
"properties": {
"base64Data": {
"type": "string",
"description": "Base64 encoded image, video, or audio binary payload (or data URI)"
},
"mediaType": {
"type": "string",
"enum": [
"auto",
"image",
"video",
"audio"
],
"description": "Media classification type (default: auto)"
},
"fileName": {
"type": "string",
"description": "Optional filename with extension (e.g. photo.jpg, vlog.mp4, interview.mp3)"
}
},
"required": [
"base64Data"
]
}🔴sanitize_media_security(base64Data, mediaType, fileName, clearGps, clearDevice, ...)
Permanently wipe and sanitize privacy metadata from image, video, or audio files (strip GPS coordinates, device fingerprints, timestamps, and comments) with zero quality loss.
入力スキーマ
{
"type": "object",
"properties": {
"base64Data": {
"type": "string",
"description": "Base64 encoded image, video, or audio binary payload (or data URI)"
},
"mediaType": {
"type": "string",
"enum": [
"auto",
"image",
"video",
"audio"
],
"description": "Media classification type (default: auto)"
},
"fileName": {
"type": "string",
"description": "Optional filename with extension (e.g. photo.jpg, vlog.mp4, note.wav)"
},
"clearGps": {
"type": "string",
"description": "Whether to erase GPS coordinates ('true' or 'false', default 'true')"
},
"clearDevice": {
"type": "string",
"description": "Whether to erase camera device fingerprints ('true' or 'false', default 'true')"
},
"clearTimestamps": {
"type": "string",
"description": "Whether to zero container recording timestamps ('true' or 'false', default 'true')"
}
},
"required": [
"base64Data"
]
}コミュニティ
エビデンス