RawMark

io.github.Sani96Published by GitHub account Sani96v1.0.0Updated Oct 25, 2026

Documents to Markdown: PDF, DOCX, PPTX, XLSX, HTML. Scanned PDF pages read by AI.

VerifiedStreamable HTTPWeb executableFiles & StorageAI & ML

Overview

AI-generated overview

RawMark converts PDF, DOCX, PPTX, XLSX, HTML and TXT files into Markdown, with AI reading of scanned PDF pages, and reports remaining plan usage.

What you can do
Convert a document to Markdown from a public file URL or from base64 content with a filename, covering PDF, DOCX, PPTX, XLSX, HTML and TXT input formats. Read scanned PDF pages through an AI vision model. Optionally use AI accuracy mode on paid plans to read every PDF page for exact tables. Check how many conversions remain on the current plan or for today's free allowance.
When to use it
Useful when an assistant needs to turn an uploaded or linked office document or PDF into Markdown text it can read, quote or process, especially when scanned pages or table-heavy PDFs are involved.
Requirements
A remote endpoint at rawmark.tech over streamable HTTP; no local runtime or package. An optional Authorization header carrying a Bearer license key enables a paid plan; without it the free plan applies with 5 conversions a day. Files must be reachable by public URL or supplied as base64 content.
Before you install
The Authorization header carries a license key, so treat it as a secret. Each conversion call consumes one conversion from the plan or the daily free allowance. Documents given by URL or base64 are sent to a third-party service, and scanned or AI-accuracy pages are processed by an AI vision model, so avoid confidential files.

Installation

In SourceWeft

  1. Open RawMark in the dashboard and add it to a workspace.
  2. 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.Sani96%2Frawmark/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.

{
  "mcpServers": {
    "rawmark": {
      "type": "http",
      "url": "https://rawmark.tech/mcp"
    }
  }
}

Tools

2

convert_document

Convert a document to Markdown

Convert a PDF, DOCX, PPTX, XLSX, HTML or TXT file to Markdown. Give either `url` (a public link to the file) or `content_base64` plus `filename`. Scanned PDF pages are read by an AI vision model. `ai_accuracy` (paid plans) reads every PDF page with AI for exact tables. Each call uses one conversion.

Parametersurlfilenameai_accuracycontent_base64

get_usage

RawMark usage

What the caller's RawMark plan has left: conversions for a license key, or today's free conversions.

Takes no parameters.

Version history

1
  1. v1.0.0LatestOct 12, 2026

Score

83% 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 listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.