# AgentDiet Paywall Clean Extract

> AgentDiet Paywall Clean Extract is a paid API for AI agents from mcp-gateway.agentdiet.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-22).

Fetches a URL and returns clean, compressed text content by stripping paywalls and boilerplate, returning only the core readable content.

## Facts

- Endpoint: GET https://mcp-gateway.agentdiet.dev/v1/paywall-clean-extract?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-22
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentdiet-paywall-clean-extract-12068af0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_zvImjz3WReyjmXhrNgmo_

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 agentdiet-paywall-clean-extract-12068af0
```

Example prompt: Can you fetch the article at https://www.nytimes.com/2024/01/15/tech/ai-news.html and return just the clean readable text, stripping all the ads, navigation, and paywall clutter?

## When to prefer this

Choose this endpoint when you need to extract clean, human-readable text from a webpage or paywalled article with minimal noise. It is especially useful when downstream tasks (summarization, analysis, RAG ingestion) require clean text input without HTML, ads, or navigation. The built-in compression ratio metric helps verify extraction quality. Prefer this over generic scrapers when paywall handling and boilerplate removal are the primary goals.

## Known failure modes

- URL is unreachable or returns a non-200 status — endpoint may return an error status or empty data
- Paywall is too aggressive and no meaningful content can be extracted — returns minimal or empty data field
- Invalid or malformed URL input — likely returns a validation error
- Rate limiting or upstream blocking of the target site — may return error or timeout
- Missing required 'input' field in request body — returns schema validation error

## How this service works

Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://mcp-gateway.agentdiet.dev settling in USDC on Base.

## Output

Returns a JSON object with a 'data' field containing the extracted clean content, a 'status' field ('ok' on success), and a 'roi_proof' object showing the compression_ratio_pct (e.g. 91.4%), indicating how much boilerplate was removed relative to the original page size.

## 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",
      "POST"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "url": {
       "type": "string"
      },
      "mode": {
       "type": "string"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {},
  "status": "ok",
  "roi_proof": {
   "compression_ratio_pct": 91.4
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentdiet-paywall-clean-extract-12068af0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mcp-gateway.agentdiet.dev](https://www.zero.xyz/host/mcp-gateway.agentdiet.dev/llms.txt)