Web content for AI agents — no subscriptions, no sign-ups.
WebFetch is a simple API that turns any webpage into clean, readable text. AI agents use it to grab articles, docs, and site content — paying just half a cent per page through an automatic micropayment system. No monthly fees, no accounts, no human in the loop.
Like a retriever, but for URLs.
Your agent sends a URL. We fetch it in a real browser, strip the cruft, and hand back clean Markdown. The whole thing costs half a cent.
Agent sends a URL
Your agent calls POST /fetch with any web URL. No account, no API key, no human.
402 — Payment Required
The API returns payment terms. Your agent's crypto wallet automatically signs a micro-payment of $0.005 in USDC and sends it back.
Browser renders the page
We run a real headless Chromium on Cloudflare's edge. JavaScript, SPAs, dynamic content — everything works.
Clean Markdown delivered
We strip ads, nav, scripts. What comes back is the content — readable, structured, LLM-ready.
$ curl -X POST https://webfetch.app/fetch \
-H "Content-Type: application/json" \
-d '{"url":"https://example.com/article"}'
→ 402 Payment Required — $0.005 USDC on Base
→ Agent signs payment with x402 wallet
$ curl -X POST https://webfetch.app/fetch \
-H "Content-Type: application/json" \
-H "Payment-Signature: <signed-payload>" \
-d '{"url":"https://example.com/article"}'
# Article Title
Here's the full article content in clean,
readable Markdown. No ads. No nav bars.
No cookie consent popups. Just the text.
$ ▌
Simple. Usage-based. Agent-ready.
No subscriptions. No commitments. Pay exactly what you use.
PAY PER FETCH
- No account required
- No API key to manage
- Agent pays autonomously
- Any URL, any format
One command. Zero setup.
WebFetch publishes an MCP server at webfetch.app/mcp. Add the URL to your MCP client config and any compatible tool discovers it as a native tool. No API keys, no sign-up.
{
"mcpServers": {
"webfetch": {
"url": "https://webfetch.app/mcp"
}
}
}
// Agent auto-discovers tool: webfetch_fetch(url)
→ x402 payment: $0.005 USDC
→ Markdown delivered
How MCP works
Add the WebFetch MCP server URL to your MCP client config. Your agent auto-discovers the webfetch_fetch tool and calls it whenever it needs web content. No curl commands, no API keys, no copy-paste. The agent handles the x402 micropayment through its wallet — $0.005 per page in USDC on Base.
One endpoint is all you need.
Works with any HTTP client. No SDK required. Just POST a URL and get back clean Markdown.
POST /fetch
Send a URL, get Markdown. First call returns 402 with payment instructions. Pay via x402, retry with signature, get content.
https://webfetch.app/fetch# Request body
{
"url": "https://example.com/article",
"options": {
"waitUntil": "networkidle0",
"timeout": 15000
}
}
# Response (200 — Paid)
{
"success": true,
"url": "https://example.com/article",
"markdown": "# Article Title\n\nContent...",
"metadata": { "title": "...", "browserMs": 2340, "chars": 12450 }
}
# Response (402 — Payment Required)
HTTP 402 Payment Required
PAYMENT-REQUIRED: <base64-payment-instructions>
# Client retries with payment signature
PAYMENT-SIGNATURE: <signed-payload>
Questions agents would ask if they could.
But since they can't, here's what their humans want to know.
What is x402 and why should I care?
Do I need a crypto wallet to use WebFetch?
What kind of pages work?
How is this different from Firecrawl?
Do you respect robots.txt and site blocklists?
robots.txt before fetching. If a site explicitly disallows crawling, we return an error. If a publisher contacts us ([email protected]), we add their domain to our blocklist immediately.
What's with the dog?
Does WebFetch work with Claude Code, Cursor, or other AI tools?
webfetch.app/mcp. Any tool that supports MCP — Claude Code, Cursor, OpenCode, Codex — can discover and use WebFetch as a native tool by adding the server URL to their MCP config. Your agent just needs a wallet with a little USDC on Base to pay per fetch.
Terms of Service
1. Service Description. WebFetch is a URL-to-Markdown conversion API. You submit a URL and we return the rendered page content as Markdown. The service is intended for use by AI agents and automated systems via the x402 micropayment protocol.
2. Payment Terms. Usage is billed per request via the x402 protocol in USDC on the Base network. The current price is listed on our pricing page and may be updated with notice. You are responsible for all charges associated with your wallet address. All payments are final and non-refundable. WebFetch does not store, hold, or custody any cryptocurrency — payments are direct wallet-to-wallet.
3. Acceptable Use. You agree not to use WebFetch to:
(a) Violate any applicable law or third-party rights, including copyright;
(b) Fetch content from sites that explicitly block automated access via robots.txt or other technical measures;
(c) Bypass authentication, paywalls, or access controls;
(d) Distribute fetched content in a way that misrepresents its source or ownership.
You are solely responsible for how you use content delivered through WebFetch. Compliance with copyright law, fair use, and platform terms falls on you as the user of the API.
4. Blocklists. WebFetch maintains both a built-in blocklist of major paywalled news domains and a dynamic blocklist for any site that requests removal. These lists are enforced at the API level and cannot be overridden. If you are a publisher and wish to block your domain, contact us at [email protected].
5. Copyright & DMCA.
5.1 Notice. If you believe content accessible through WebFetch infringes your copyright, send a written notice to [email protected] containing substantially the following:
(i) Your physical or electronic signature;
(ii) Identification of the copyrighted work claimed to be infringed;
(iii) Identification of the infringing material and information sufficient to locate it (the URL);
(iv) Your name, address, telephone number, and email address;
(v) A statement that you have a good faith belief that the use is not authorized by the copyright owner, its agent, or the law;
(vi) A statement, under penalty of perjury, that the information in the notice is accurate and that you are authorized to act on the copyright owner's behalf.
5.2 Takedown. Upon receipt of a valid notice, we will expeditiously remove or disable access to the identified material and notify the user who posted it.
5.3 Counter-Notice. If you believe material was removed due to mistake or misidentification, you may submit a counter-notice containing: (i) your signature; (ii) identification of the removed material and its location before removal; (iii) a statement under penalty of perjury of good faith belief that the removal was a mistake; (iv) your name, address, and phone number, and consent to federal court jurisdiction. We will forward the counter-notice to the original claimant. Unless the claimant informs us of a court action within 10-14 business days, we will restore the material.
5.4 DMCA Agent. Registration with the U.S. Copyright Office is pending. Until registered, safe harbor protections under 17 U.S.C. § 512 may not apply. Contact: [email protected].
6. No Warranty. The service is provided "as is" and "as available" without warranty of any kind, express or implied. We do not guarantee that every URL will render successfully, that content will be complete or accurate, or that the service will be uninterrupted or error-free.
7. Limitation of Liability. To the maximum extent permitted by law, WebFetch and its operators shall not be liable for any indirect, incidental, special, consequential, or punitive damages arising from your use of the service. Our total liability for any claim shall not exceed the amount paid by you to WebFetch in the 12 months preceding the claim.
8. Indemnification. You agree to indemnify and hold WebFetch harmless from any claims, damages, or expenses arising from your use of the service or violation of these terms.
9. No Accounts. WebFetch does not create accounts, store credentials, or collect personal information. The service is fully anonymous. No data about individual users is retained beyond aggregate usage statistics stored in KV by month.
10. Changes. These terms may be updated at any time. We will indicate the date of the last update. Continued use after changes constitutes acceptance of the revised terms.
11. Governing Law. These terms are governed by the laws of the State of Ohio, United States, without regard to conflict of law principles.
12. Contact. General inquiries: [email protected]. DMCA: [email protected].
Last updated: July 23, 2026.