# Web Page to Clean Markdown Scraper

> Web Page to Clean Markdown Scraper is a paid API for AI agents from store.agentexchange.work, paid per call via x402, $0.09/call, status unknown (last checked 2026-09-14).

Fetches any webpage URL and returns clean, ad-free, nav-free Markdown optimized for LLM context, RAG pipelines, and autonomous agent research.

## Facts

- Endpoint: GET https://store.agentexchange.work/web/markdown-scraper
- Price: $0.09/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/web-page-to-clean-markdown-scraper-bb28ae14
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Io8dr660Lk4h0W-r148x7

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability web-page-to-clean-markdown-scraper-bb28ae14
```

Example prompt: Fetch https://en.wikipedia.org/wiki/Retrieval-augmented_generation and give me the clean, ad-free markdown version so I can use it as context for my research.

## When to prefer this

Choose this endpoint when you need lightweight, agent-ready Markdown from any public webpage at low cost ($0.005/call), with no API key required and payment over x402/USDC. Prefer it over full HTML fetchers when you want LLM-friendly output with noise removed, or over heavier crawling services when you only need a single page's readable content.

## Known failure modes

- URL is unreachable or returns a non-200 status — likely returns an error or empty markdown
- Paywalled or JS-heavy pages may return incomplete or empty content
- Invalid or missing 'url' query parameter returns a validation error
- Payment failure via x402 protocol results in 402 response before scrape is attempted
- Rate limiting or network timeout on the target site may cause partial content

## How this service works

Converts any URL into clean, LLM-friendly Markdown for autonomous web research, bypassing basic bot protection. Essential for agents that need to read the web.

## Output

Returns a JSON object containing the source URL, a clean Markdown rendering of the page (ads, navigation, popups stripped), and a Unix timestamp of when the scrape occurred. Output is roughly 4x smaller than raw HTML.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "URL of the webpage to scrape (required)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "url": {
       "type": "string"
      },
      "markdown": {
       "type": "string"
      },
      "scanned_at": {
       "type": "number"
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com",
  "markdown": "# Example Domain\n\nThis domain is for use in illustrative examples...",
  "scanned_at": 1781832000000
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/web-page-to-clean-markdown-scraper-bb28ae14/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from store.agentexchange.work](https://www.zero.xyz/host/store.agentexchange.work/llms.txt)