# AgentDiet MCP Gateway Web Scraper

> AgentDiet MCP Gateway Web Scraper 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 and compresses the content of a given URL via a paid x402 micro-payment gateway, returning cleaned web page data with a compression ratio proof

## Facts

- Endpoint: GET https://mcp-gateway.agentdiet.dev/v1/web-scrape?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-mcp-gateway-web-scraper-64393968
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_3kVXe3ZTDOR0jvctF5Kb5

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-mcp-gateway-web-scraper-64393968
```

Example prompt: Can you scrape the content of https://example.com/about and give me the text from that page?

## When to prefer this

Choose this endpoint when you need a quick, low-cost ($0.001 USDC) web scrape of a public URL with built-in compression, and you are operating within an x402/MCP payment-enabled agent stack. Particularly useful when you want a pay-per-use model without API key management, or when your agent needs to access web content as part of a larger MCP-orchestrated workflow. Prefer alternatives if you need full JavaScript rendering, bulk crawling, or structured data extraction schemas.

## Known failure modes

- URL is unreachable or returns a non-200 HTTP status, resulting in an error response
- URL parameter missing from query params, causing a validation error
- Target page is behind authentication or a CAPTCHA, resulting in empty or blocked content
- Payment not settled in USDC on Base, causing a 402 rejection before execution
- Malformed URL input causing a parsing error
- Dynamic JavaScript-heavy pages may return incomplete content if client-side rendering is required

## 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

A JSON response containing a 'data' object with the scraped page content, a 'status' field indicating success ('ok'), and an 'roi_proof' object with a compression_ratio_pct value showing how much the content was compressed (e.g. 91.4%).

## 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-mcp-gateway-web-scraper-64393968/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)