PDF & Office to Markdown for RAG

io.github.BrunenJerePublished by GitHub account BrunenJerev0.1.1Updated Nov 5, 2026

Converts PDF, scans, DOCX, XLSX and PPTX to Markdown with tables and page-aware RAG chunks.

VerifiedStreamable HTTPWeb executableFiles & StorageKnowledge & Memory

Overview

AI-generated overview

Remote Apify-hosted MCP server that converts PDFs, scans and Office files into Markdown, tables and page-aware chunks for RAG indexing.

What you can do
  • Convert PDF, DOCX, HTML and scanned documents into Markdown, with OCR for scans
  • Extract tables and split documents into page-aware chunks ready for a vector index
  • Run alongside two other pay-per-use tools on the same endpoint: Argentine invoice (ARCA/AFIP) extraction to JSON and audio/video transcription with timestamps, SRT, VTT and timed chunks
When to use it
Useful when you want an assistant to turn a pile of PDFs, scans or Office documents into clean Markdown and chunked text for a retrieval index, without running your own conversion pipeline.
Requirements
A remote MCP endpoint at mcp.apify.com with an Apify account. An Apify API token is sent as an Authorization bearer header (APIFY_TOKEN in some client setups). Network access is required; no local runtime or package is installed.
Before you install
Usage is billed per event by Apify: USD 0.001 per page, USD 0.003 per OCR page, plus per-invoice and per-minute rates for the other tools. The Apify token is a billable credential and should be kept in secure storage. Uploaded files are processed in your Apify run and stored under your Apify account's retention settings.

Installation

In SourceWeft

  1. Open PDF & Office to Markdown for RAG in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.BrunenJere%2Fdocuments-to-markdown-rag/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "pdf-office-to-markdown-for-rag": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=lif_manager/documents-to-markdown-rag"
    }
  }
}

README

LIF Tools

Three pay-per-use tools for AI agents, plus a free skill. They run on Apify: you bring your own Apify token and Apify bills each run. There is no subscription.

ToolWhat it returnsPrice
Argentine invoices (ARCA/AFIP) to JSONValidated JSON from a PDF or image: type, number, date, CUITs, net, VAT, total, CAE. It checks the CUIT check digit, the totals and the QR against the text.USD 0.01 per invoice
Documents to Markdown for RAGMarkdown, tables and chunks ready for a vector index, from PDF, DOCX, HTML and scans (OCR).USD 0.001 per page, USD 0.003 per OCR page
Audio and video transcriptionText with timestamps, SRT, VTT, Markdown and timed chunks. Spanish first, many languages.USD 0.010 per minute (USD 0.004 fast mode)

The comprobantes-ar skill (Spanish) validates Argentine invoices locally with no network calls, using only the Python standard library.

Install

Claude Code

/plugin marketplace add BrunenJere/lif-tools/plugin install lif-tools@lif

Claude Code asks for your Apify token when you enable the plugin and keeps it in secure storage.

Antigravity: install LIF Tools from the plugin marketplace, or from this repository. It asks for APIFY_TOKEN during setup.

Any MCP client: add the remote server https://mcp.apify.com/?tools=lif_manager/facturas-arca-json,lif_manager/documents-to-markdown-rag,lif_manager/audio-video-transcription with the header Authorization: Bearer <your Apify token>. The servers are also in the official MCP Registry as io.github.BrunenJere/*.

Limits

  • The invoice tool does not query ARCA. Verifying an invoice officially needs the issuer's certificate.
  • Uncommon invoice layouts may leave fields as no_disponible. The tool reports this and does not guess.
  • None of the tools give accounting or legal advice.
  • Files you send are processed in your Apify run and stored under your Apify account's retention settings. LIF does not keep them.

Privacy

See PRIVACY.md.

License

MIT for the files in this repository. The Apify tools are services billed per use.

Source: README.md at commit a88f95f

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

2
  1. v0.1.1LatestNov 5, 2026
  2. v0.1.0Nov 4, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts