Guide

Start in Account. Only open Chrome or Edge when the paper page itself needs local capture.

Most people only need one path: open Account for keyword discovery and API-key management, create a key, and send Mdtero to the agent they already use. Chrome or Edge is the secondary path when a live paper page has to be captured on your own machine.

Open Account Open API guide Install from Chrome Web Store Install from Edge Add-ons

Account is the normal setup path. The local helper handles acquisition by default, and Chrome or Edge is only for pages that must be captured in a browser.

Quick Start

Most people only need this path

Keep the default path simple: set up your agent in Account first, then install Chrome or Edge only if a live paper page must be captured locally.

Open Account

Create or select a key, then generate the setup message for your agent.

Open Chrome or Edge only if needed

Install Mdtero in Chrome or Edge only when helper-driven acquisition needs a live browser page on your own machine.

Add Elsevier only when required

Use your own Elsevier key only when you need the local helper to retrieve Elsevier XML on your own machine.

Translate after parsing if needed

Generate a translated Markdown copy only when you want a reading version in another language.

Good to know

A few cases worth knowing before you start

Most people can stop at Account and keep moving. These notes only matter when your reading workflow is a little more specific.

Agent

Connect Mdtero to your agent

OpenClaw, Claude Code, Codex, and Gemini CLI all start from the Account message with your setup already prepared.

ClawHub installs the agent skill only. Install the local helper separately when local acquisition is needed. Markdown is the default handoff, and PDF only matters when a workflow really needs it.

Browser stores

Use Chrome or Edge only when you need local capture

Install the extension when you are already on a supported paper page and want that capture to stay on your own machine.

Open the Chrome Web Store or Edge Add-ons listing.
Add Mdtero to the browser you already use and pin it if you capture often.
Skip this entirely when Account plus agent handoff is enough.

Open the Mdtero Chrome Web Store page Open the Mdtero Edge Add-ons page

Supported Sources

What works well right now

Most papers follow the same flow: start in Account or the local helper, and only bring in Chrome or Edge when a live publisher page must be captured locally.

Elsevier

Best for structured publisher XML, remote figure links, source downloads, and full parsing with your own developer key on a machine that already has access.

arXiv

Best for HTML-first preprints, faster starts, and carrying figures plus Markdown into your reading workflow.

Springer / Nature / RSC

When a live publisher page has to stay on your own machine first, use browser capture as the fallback path before handing the Markdown back to the rest of your workflow.

OpenClaw on Server

Is your OpenClaw running on a server?

Keep local or campus-bound acquisition on your own machine first, then pass the Markdown output back to OpenClaw for the rest of the workflow.

If Elsevier only returns the abstract, first check whether the local machine is actually on a campus or institutional network IP.

OpenClaw node docs

Recommended

Use a local Mdtero node for acquisition

Run the Mdtero local helper on the machine that has the right network access. In OpenClaw, connect that machine as a node or execution target so the server-side session can call it only for the acquisition step.

Keep your main OpenClaw deployment on the server.
Install the Mdtero local helper on your campus-network laptop or desktop.
Register that machine as an OpenClaw node so the server workflow can delegate local retrieval there.
Return the parsed Markdown, or the fallback ZIP when needed, to the server session for translation, review, and downstream agent work.

Fallback

Use helper + browser capture, then hand the Markdown to OpenClaw

If you do not want to wire a node yet, run the Mdtero helper on your own computer and let it hand off to the browser extension only when a live page requires browser capture. Then upload or paste the resulting Markdown into your OpenClaw workflow.

Open the paper locally in Chrome or Edge.
Use the Mdtero extension to parse and download the Markdown.
Send the Markdown file, or the fallback ZIP when needed, to your OpenClaw session.
Let OpenClaw continue with translation, comparison, summarization, or review writing.

Bring your own access

Already able to open the article yourself?

If the paper opens through your campus network, library, or personal account, Mdtero can work from that access on your own machine.

You do not need extra setup for this guide unless a source specifically asks for it later.

API

Do you need scripts or product integration?

Authentication, endpoints, and automation examples live on the API page so this guide can stay short.

Open API guide

Open source

Need the public client repository?

If you need helper install files, extension code, or public setup references, use the single public repository. Normal users should still start from the product site and Account flow.

Open doi2md repo

Downloads

What you get back

Markdown
humbert2023topology.md
Embedded figures in humbert2023topology.md
Translated Markdown

PDF is optional. Mdtero is designed to start from the structured Markdown file first, then fall back to source-side PDF or a ZIP only when a workflow truly needs it.

Plans and usage

Keep pricing and access transparent

Source downloads stay visible. Plans cover routine work, translation add-ons handle overflow, and balance stays available for flexible API use.

Launch rewards now come from campaign codes, temporary trials, and referral bonuses rather than automatic sign-up gifts.