Skip to content

Your agent deservesbetter data.

Every parse returns clean Markdown plus Litmus — twenty deterministic signals on who wrote the page, how fresh it is, and whether it is even the page you asked for.

10 free parses a month · no account · no API key

POST nanoparse.app/fetch
$0.002
Samples
clean.md108 words

Diet and longevity: a 20-year cohort study

By Jane Chen · The Lancet · 14 Jan 2026

A comprehensive 20-year study published in The Lancet has found a strong correlation between dietary patterns and increased lifespan.

Key figures

DietAvg lifespanSample
Mediterranean83.4 yrn=12,400
Standard Western76.1 yrn=11,800

Researchers noted that participants following a Mediterranean diet showed a 7.3-year increase in average life expectancy compared to the control group.

The study controlled for socioeconomic factors and exercise habits across 24,200 participants in seven countries.

200 OK1.42s20 signals
$0.002
per parse, flat
20
deterministic signals
10
free parses / month
x402
USDC on Base
Plug into the hosts your agent already uses
Claude CodeCursorWindsurfClineZedRaycastany MCP hostClaude CodeCursorWindsurfClineZedRaycastany MCP host
The gap

Your agent can read any page.It cannot tell whether to believe it.

Extraction solved the text problem and left the judgement problem alone. Each of these is something an agent gets wrong today — confidently, and in writing.

01

Stale, cited as current

No publish date, no staleness flag. A 2019 explainer reads exactly like last week's — and the citation looks identical either way.

02

A paywall read as content

A login wall or truncated teaser passes as the article. The agent summarises the first eighty words of a page it never actually read.

03

An error page read as content

A soft 404, a captcha, a "please enable JavaScript" shell — all arrive with a 200 status and get treated as a source.

04

A copy read as the original

Thin pages, syndicated reposts and boilerplate-heavy layouts rank like primary sources, because nothing measured the difference.

Twenty checks · deterministic

Twenty data points before your agent cites a page.

Every parse returns clean Markdown plus Litmus — twenty rule-based checks on who wrote the page, how fresh it is, and whether it is even the page that was asked for. No model in the path.

Source

6 signals

Who wrote it, what it claims to be, who it links to, and whether it shows its work.

Page type, authority score, and the reasoning behind it.

type: "news" · authority: 0.82
type: "blog" · authority: 0.21
Read the full signal referencesame input · same signals · every time
Determinism

No model in the path.Same page, same verdict.

A model can form an opinion about a page. The problem is what happens on the second run. Litmus is rule-based and extractive, so a given page and version produce the same signals every time — and the verdict can be logged and audited.

“A judge that changes its mind is not a judge you can log.”
determinism.log identical
run 1verdict=cite trust=high density=0.78
run 2verdict=cite trust=high density=0.78
diff0 signals changed

A model in the path

  • Different verdict on the same page tomorrow
  • Unbounded cost per call, paid in tokens
  • No audit trail — "the model said so"
  • Confident when wrong, with no field to check

Determinism in the path

  • Same signals on the same page, always
  • Fixed cost — $0.002, metered per call
  • Every field inspectable in the payload
  • Fails visibly — null and "unknown", never a guess
Payments

x402. USDC on Base.$0.002 per parse.

No account, no API key, no subscription. An agent discovers the endpoint, pays per parse, machine to machine, and is charged only when the page renders.

per successful parse
$0.002flat
10 free parses a month
No account or API key
Failed parses never charged
Settlement only after render

On a cloud host the anonymous allowance does not apply: sign with your wallet once and claim the same 10, no payment and no account. How the claim works

x402 payment loop
v2
self-custodied walletready$0.002
network
eip155:8453
scheme
exact
gas
absorbed
asset
USDC
Integration

One config. Then your agent has the web.

No SDK, no build step. Add the MCP server and the agent discovers both tools — fetch a URL, or check its quota and wallet state.

  • MCPnanoparse_fetch(url) → markdown + litmus
  • MCPnanoparse_status() → quota, wallet, payment
  • RESTPOST /fetch · OpenAPI at /openapi.json
mcp.json
{  "mcpServers": {    "nanoparse": {      "type": "http",      "url": "https://nanoparse.app/mcp"    }  }}// The agent discovers two tools:// nanoparse_fetch(url)  -> markdown + litmus// nanoparse_status()    -> quota, wallet, payment

typically 2–8 seconds per parse · results held 6 hours

Compare

Other tools extract. Litmus judges.

Full comparison
SignalExtractionA modelLitmus
Clean MarkdownYesYesYes
JavaScript renderedSometimesDependsYes
Named author or anonymous—SometimesYes
Freshness + staleness warning—SometimesYes
Same input, same outputYesNoYes
FAQ

Questions agents would ask.

Straight answers for developers wiring up NanoParse.

Yes. Standard scrapers fail on modern SPAs because they only fetch raw HTML. NanoParse renders each page in headless Chromium, executes JavaScript, and waits for dynamic content to settle before running content isolation. The Markdown you get back is what a human would have seen.

Test the page. Then trust it.

Run it on a page you already trust, then on one you don't. The difference in the payload is the pitch.

10 free parses a month · no account · no API key

20 signalsdeterministic$0.002 / parse