document-processing
Extract text from documents, manipulate PDFs, and perform OCR on images.
使うべきか
品質と安全性
検出事項（6）
- LOWTool 'filegraph_pdf_manipulation_docs' description lacks action verbfilegraph_pdf_manipulation_docs 内
- LOWTool 'filegraph_pdf_security_docs' description lacks action verbfilegraph_pdf_security_docs 内
- LOWTool 'filegraph_pdf_text_conversion_docs' name length outside 3-30 rangefilegraph_pdf_text_conversion_docs 内
- LOWTool 'filegraph_pdf_manipulation_docs' name length outside 3-30 rangefilegraph_pdf_manipulation_docs 内
- LOWTool 'filegraph_image_processing_docs' name length outside 3-30 rangefilegraph_image_processing_docs 内
- LOWTool 'filegraph_office_documents_docs' name length outside 3-30 rangefilegraph_office_documents_docs 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": {
"document-processing": {
"url": "https://api.filegraph.ai/mcp"
}
}
}リモートエンドポイント
https://api.filegraph.ai/mcpstreamable-httphttps://api.filegraph.ai/mcpsseできること
ツール一覧
ツール（9）
⚪filegraph_api_overview
API overview: authentication, rate limits, errors, and available endpoint groups.
入力スキーマ
{
"type": "object",
"properties": {},
"required": []
}🟢filegraph_text_extraction_docs(language, endpoint)
Docs for /any/to-text, /any/info, /any/to-struct — extract text with smart format detection and ocr, analyze file metadata, extract structured data with LLM.
入力スキーマ
{
"type": "object",
"properties": {
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Language",
"description": "Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX."
},
"endpoint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Endpoint",
"description": "Get docs for a single endpoint only (reduces response size). Valid values: /any/to-text, /any/info, /any/to-struct"
}
},
"required": []
}🟢filegraph_pdf_text_conversion_docs(language, endpoint)
Docs for /pdf/to-text, /pdf/to-docx, /pdf/to-image — extract text with ocr, convert pdf to docx or images.
入力スキーマ
{
"type": "object",
"properties": {
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Language",
"description": "Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX."
},
"endpoint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Endpoint",
"description": "Get docs for a single endpoint only (reduces response size). Valid values: /pdf/to-text, /pdf/to-docx, /pdf/to-image"
}
},
"required": []
}⚪filegraph_pdf_manipulation_docs(language, endpoint)
Docs for /pdf/merge, /pdf/split, /pdf/compress, /pdf/rotate — merge, split, compress, and rotate pdf files.
入力スキーマ
{
"type": "object",
"properties": {
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Language",
"description": "Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX."
},
"endpoint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Endpoint",
"description": "Get docs for a single endpoint only (reduces response size). Valid values: /pdf/merge, /pdf/split, /pdf/compress, /pdf/rotate"
}
},
"required": []
}⚪filegraph_pdf_security_docs(language, endpoint)
Docs for /pdf/encrypt, /pdf/decrypt — encrypt and decrypt pdf files with password protection.
入力スキーマ
{
"type": "object",
"properties": {
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Language",
"description": "Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX."
},
"endpoint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Endpoint",
"description": "Get docs for a single endpoint only (reduces response size). Valid values: /pdf/encrypt, /pdf/decrypt"
}
},
"required": []
}🟢filegraph_image_processing_docs(language, endpoint)
Docs for /image/to-text, /image/to-pdf, /image/resize — extract text via ocr, convert images to pdf, resize images.
入力スキーマ
{
"type": "object",
"properties": {
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Language",
"description": "Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX."
},
"endpoint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Endpoint",
"description": "Get docs for a single endpoint only (reduces response size). Valid values: /image/to-text, /image/to-pdf, /image/resize"
}
},
"required": []
}🟢filegraph_office_documents_docs(language, endpoint)
Docs for /docx/to-text, /docx/to-pdf, /xlsx/to-text, /xlsx/to-pdf, /xlsx/to-csv, /pptx/to-text, /pptx/to-pdf, /pptx/to-images — extract text/data, convert word/excel/powerpoint to pdf/csv/images.
入力スキーマ
{
"type": "object",
"properties": {
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Language",
"description": "Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX."
},
"endpoint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Endpoint",
"description": "Get docs for a single endpoint only (reduces response size). Valid values: /docx/to-text, /docx/to-pdf, /xlsx/to-text, /xlsx/to-pdf, /xlsx/to-csv, /pptx/to-text, /pptx/to-pdf, /pptx/to-images"
}
},
"required": []
}🟢filegraph_html_processing_docs(language, endpoint)
Docs for /html/to-text, /html/to-pdf, /html/to-image — extract html text, render to pdf, capture html screenshots.
入力スキーマ
{
"type": "object",
"properties": {
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Language",
"description": "Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX."
},
"endpoint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Endpoint",
"description": "Get docs for a single endpoint only (reduces response size). Valid values: /html/to-text, /html/to-pdf, /html/to-image"
}
},
"required": []
}⚪filegraph_security_docs(language, endpoint)
Docs for /security/pdf/redact, /security/text/redact, /security/pdf/lock, /security/pdf/unlock, /security/detect-tracking — redact sensitive pdf content, redact PII from extracted text, lock/unlock pdfs, detect/remove tracking pixels.
入力スキーマ
{
"type": "object",
"properties": {
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Language",
"description": "Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX."
},
"endpoint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Endpoint",
"description": "Get docs for a single endpoint only (reduces response size). Valid values: /security/pdf/redact, /security/text/redact, /security/pdf/lock, /security/pdf/unlock, /security/detect-tracking"
}
},
"required": []
}コミュニティ
エビデンス