ai.filegraph/document-processing

设计与媒体 HTTP 只读/查询为主

能做什么：这组工具返回的是能力文档：文本提取、PDF 转文本、PDF 拆分合并与加密、图片 OCR 和 Office 文档处理的接口说明。

什么时候接：要批量处理 PDF 或扫描件之前，先读它的接口说明确认能不能做，再决定自己写脚本还是接它的 API。

注意：工具本身只给文档说明，不直接处理文件，实际调用需按其 API 接入；能力边界与配额以官方 README 为准。

可用工具

filegraph_api_overviewAPI overview: authentication, rate limits, errors, and available endpoint groups.
filegraph_text_extraction_docsDocs 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.
filegraph_pdf_text_conversion_docsDocs for /pdf/to-text, /pdf/to-docx, /pdf/to-image — extract text with ocr, convert pdf to docx or images.
filegraph_pdf_manipulation_docsDocs for /pdf/merge, /pdf/split, /pdf/compress, /pdf/rotate — merge, split, compress, and rotate pdf files.
filegraph_pdf_security_docsDocs for /pdf/encrypt, /pdf/decrypt — encrypt and decrypt pdf files with password protection.
filegraph_image_processing_docsDocs for /image/to-text, /image/to-pdf, /image/resize — extract text via ocr, convert images to pdf, resize images.
filegraph_office_documents_docsDocs 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.
filegraph_html_processing_docsDocs for /html/to-text, /html/to-pdf, /html/to-image — extract html text, render to pdf, capture html screenshots.
filegraph_security_docsDocs 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.

更新日期：2026-10-29（tools/list 实测）

{
  "mcpServers": {
    "remote-ai-filegraph-document-processing": {
      "type": "http",
      "url": "https://api.filegraph.ai/mcp"
    }
  }
}

资料来自官方仓库与 MCP 接口探测，以官方最新文档为准；安装第三方 MCP server 前请自行评估安全风险。