Fetch and Read
Fetch and Read
Turn any public web page into clean markdown an agent can actually read. Strips scripts, navigation, sidebars, cookie banners and comment threads, resolves every link to an absolute URL, and returns the title, site name and publication date alongside the text. Handles JSON and plain text too. Use it after a search tool: search gives you links, this reads them.
$0.0040 a run5 runs, every one worked
https://www.rfc-editor.org/rfc/rfc7231.txt
{
"title": "",
"finalUrl": "https://www.rfc-editor.org/rfc/rfc7231.txt",
"markdown": "Internet Engineering Task Force (IETF) R. Fielding, Ed.\nRequest for Comments: 7231 Adobe\nObsoletes: 2616 J. Reschke, Ed.\nUpdates: 2817 greenbytes\nCategory: Standards Track June 2014\nISSN: 2070-1721\n\n\n Hypertext Transfer Protocol (HTTP/1.1): Semantics and Content\n\nAbstract\n\n The Hypertext Transfer Protocol (HTTP) is a stateless application-\n level protocol for distributed, collaborative, hypertextCut short here. Run it to get the whole answer.
Run Fetch and Read from anywhere
Right here
Fill in the box above and the answer comes straight back. No account, no signup.
Open the run box →In your Discord server
Add the amnt bot to your server. Anyone types /run, picks Fetch and Read from the list, and the answer appears in the channel for everyone to see. Each person links their amnt account once with /link so their own credits pay for their own runs.
Add the bot to Discord →/run agent: fetch-and-read prompt: what you wantFrom Claude, Cursor, or any MCP client
Point your MCP client at amnt with an API key and Fetch and Read shows up as a tool your assistant can call on its own.
How to connect →https://www.amnt.io/api/mcpFrom your own code
One HTTP call with an API key. Credits are charged per run and the result comes back in the same response.
Developer docs →curl -X POST https://www.amnt.io/api/v1/run \ -H "Authorization: Bearer amnt_sk_..." \ -H "Content-Type: application/json" \ -d '{"agent":"amnt/fetch-and-read","input":{"prompt":"..."}}'
What it costs
No subscription, no minimum, no account. Pay with a card or a Hedera wallet. The creator earns 70% of every run.
Questions
- What does Fetch and Read do?
- Fetch and Read is Turn any public web page into clean markdown an agent can actually read. Strips scripts, navigation, sidebars, cookie banners and comment threads, resolves every link to an absolute URL, and returns the title, site name and publication date alongside the text. Handles JSON and plain text too. Use it after a search tool: search gives you links, this reads them., created by @amnt. Describe what you want, pay once, and get the result in the same response.
- How much does Fetch and Read cost?
- $0.0040 per run. You only pay when you use it - no subscription, no monthly fee, no minimum spend.
- Do I need an account to use Fetch and Read?
- No account and no email needed. Pay with a card or a Hedera wallet and you are ready. There is nothing to subscribe to and nothing to cancel.
- Can I call Fetch and Read from my own code?
- Yes. POST to /api/agent/amnt/fetch-and-read with an x402 payment header and the required inputs. The result comes back in the same HTTP response - no API key, no account.
Details
How it works, proof it works, and how to call it from code
How it's performing
Three steps
- Tell it what you want
Fill in the box. No prompt-writing - the recipe is already built in.
- Pay once, per run
$0.0040 a run. No subscription, no minimum, no account. You pay only when you press run.
- Get the result in the same reply
Fetch and Read returns your result immediately. Run it again with different inputs any time.
Use it from your own code
Fetch and Read is a live HTTP endpoint. POST to it with an x402 payment header and the result comes back in the same response - no API key, no account.
curl -X POST https://www.amnt.io/api/agent/amnt/fetch-and-read \
-H "Content-Type: application/json" \
-H "X-Payment: <x402-payment-header>" \
-d '{ "prompt": "..." }'