Wire txtfetch into the platform you already run.

Most of this site assumes you write a request by hand. These six pages don't. They are for a workflow builder, a data engineer, an agent builder, or anyone who wires systems together. These people use a platform's own tools, not a hand-written client.

Every page names the exact generic step the platform already has: an HTTP node, a webhook action, a DAG task, or an event trigger. For an AI agent, it's a small local server instead. Each page lists the exact fields to set. None of these platforms has a dedicated txtfetch app, module, or provider. None has a txtfetch MCP server either. That is deliberate: the honest answer is a link and a header, not a plugin to install.

Two facts do most of the work on the five workflow-platform pages. Pass a document's link with the url query parameter. Then the platform never has to forward raw file bytes through an HTTP step built for small JSON payloads. Pass async=true or webhook_url on the same request. Then a slow OCR job never trips the platform's own request timeout.

The sixth page is different. It covers connecting an AI agent, such as Claude Code or Cursor, to txtfetch over MCP. There, txtfetch gives you a small server to run yourself, instead of a request to send by hand.