---
title: NanoParse — Your agent deserves better data
url: https://www.nanoparse.app/
description: "Turn any URL into clean Markdown plus Litmus: 20 deterministic trust signals on authorship, freshness, paywalls and whether it is the page you asked for. $0.002 per parse via x402."
---

[Litmus v2 — now 20 signals](https://www.nanoparse.app/litmus)

# 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.

[Run a free test](https://www.nanoparse.app/#parse)[See the 20 signals](https://www.nanoparse.app/litmus)

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

POST nanoparse.app/fetch

demo$0.002

Samples

Research paperThin landing pagePaywalled articleSoft 404

or paste any URL — 3 free demos / day

markdownlitmus

clean.md108 words

Copy

### 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

| Diet | Avg lifespan | Sample |
| --- | --- | --- |
| Mediterranean | 83.4 yr | n=12,400 |
| Standard Western | 76.1 yr | n=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.

litmus.json

overviewjson

VerdictCite

Safe to build on

Named author, dense citations, high structural trust. The page says what it claims and shows its work.

sourcenews · 0.82

authorshipJane Chen · jsonld

freshness14 Jan 2026 · current

structural_trusthigh · 0.92

citations12 external · 3.2/1k

content_density0.78 · substantive

paywallnone

reading_time7 min

+ 12 more signalsv2

200 OKsample response1.42s20 signalsdeterministic

$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.

[See the full comparison](https://www.nanoparse.app/compare)

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.

published 2019

now

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.

paywalled

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.

404page not found

200 OK

04

### A copy read as the original

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

same text

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.

Signal groups

01Source602Trust503Validity604Read3

20 of 20 active

Rule-based and extractive. No model, no temperature, no second run that disagrees with the first.

### Source

6 signals

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

01source

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

`type: "news" · authority: 0.82`

`type: "blog" · authority: 0.21`

02authorship

03content_type

04outbound_authority

05citations

06structured_data

[Read the full signal reference](https://www.nanoparse.app/litmus)same 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](https://www.nanoparse.app/quickstart#free-tier)

[Wire up the payment loop](https://www.nanoparse.app/quickstart)

x402 payment loop

v2

1. 01The agent asks`POST /fetch`A URL goes in. No account, no key, no checkout page.
2. 02The endpoint answers 402`402 Payment Required`The challenge carries price, network, payTo and a 60-second window.
3. 03The wallet signs`EIP-3009 · 2,000 units`A $0.002 USDC authorization on Base. Off-chain, no gas.
4. 04Settled, then parsed`USDC · eip155:8453`The facilitator verifies and settles. Markdown and Litmus return.

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.

- MCP`nanoparse_fetch(url) → markdown + litmus`
- MCP`nanoparse_status() → quota, wallet, payment`
- REST`POST /fetch · OpenAPI at /openapi.json`

[Quickstart](https://www.nanoparse.app/quickstart)[MCP server repo](https://github.com/nanoparse-dev/nanoparse-mcp)

MCPcURLTypeScriptPython

mcp.json

Copy

```
{ "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](https://www.nanoparse.app/compare)

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.

Still deciding?

Test a page you already trust. Then test one you don't. The difference in the payload is the pitch.

[Run a test](https://www.nanoparse.app/#parse)

Does this work on React, Vue and heavy JavaScript sites?

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.

Does my agent need a wallet?

What is x402?

What is Litmus?

How is this different from Firecrawl?

What happens when a parse fails?

![](https://www.nanoparse.app/brand/nanoparse-logo-official.svg)

## 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.

[Run a free test](https://www.nanoparse.app/#parse)[See all 20 signals](https://www.nanoparse.app/litmus)

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

20 signalsdeterministic$0.002 / parse
