stagenth doc parse

Created By
3 days ago
Parse PDF / Word / PPT / HTML into clean Markdown: doc_parse (page ranges), doc_tables (tables as JSON), doc_images (extract embedded images), doc_chunk (heading-based RAG chunks).
Overview

stagenth doc parse

Parse PDF / Word / PPT / HTML into clean Markdown: doc_parse (page ranges), doc_tables (tables as JSON), doc_images (extract embedded images), doc_chunk (heading-based RAG chunks).

Tools

  • doc_parse — PDF / .docx / .pptx / HTML / txt / md to clean Markdown + per-page structure; supports page_range like 3-10 (billed per parsed page)
  • doc_tables — extract document tables as headers+rows JSON that AI can compute on directly
  • doc_images — extract embedded images (icons filtered), delivered as a ZIP download
  • doc_chunk — split a document into heading-based semantic chunks sized for RAG / embeddings

Connect

  1. Sign up at https://www.stagenth.com and create an API token (Console → API Tokens).
  2. Add to your MCP client config:
{"mcpServers":{"stagenth-doc-parse":{"type":"http","url":"https://stagenth.com/mcp/doc-parse/","headers":{"Authorization":"Bearer <YOUR_API_KEY>"}}}}

Docs: https://www.stagenth.com/help?scope=agent-tools

Server Config

{
  "mcpServers": {
    "stagenth-doc-parse": {
      "type": "http",
      "url": "https://stagenth.com/mcp/doc-parse/",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}
Project Info
Created At
3 days ago
Updated At
3 days ago
Author Name
-
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Kudosity

6 hours ago
Mapquest Mcp

12 hours ago