# Easy Reader AI – Metadata Endpoint

> Easy Reader AI – Metadata Endpoint is a paid API for AI agents from agent-reader.gm-tools.workers.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-13).

Fetches metadata (title, language, description) for a given public web page or PDF URL, returning structured JSON, paid per call via x402/USDC.

## Facts

- Endpoint: GET https://agent-reader.gm-tools.workers.dev/v1/meta?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/easy-reader-ai-metadata-endpoint-0665ced9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_LJ-4F5I2NUrqH2oiRZP8g

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 easy-reader-ai-metadata-endpoint-0665ced9
```

Example prompt: Can you pull the title, language, and description metadata for https://openai.com/research/gpt-4 — I just need the structured page info, not the full content.

## When to prefer this

Choose this endpoint when you need lightweight, structured page metadata (title, language, description) from a public URL without paying for full-page Markdown extraction. It is ideal for link enrichment, language detection, or content cataloguing workflows where you don't need the full text. Since it requires no API key or signup and charges only per successful call in USDC via x402, it suits agent pipelines that need zero-friction, pay-as-you-go access.

## Known failure modes

- URL is not publicly accessible (private, paywalled, or 404) — request may fail and will not be charged
- URL points to a non-HTTP(S) resource — rejected by schema validation
- Malformed or missing 'url' query parameter — returns validation error
- Timeout on slow or very large pages — request fails uncharged
- PDF parsing failure for malformed documents — returns error, no charge

## How this service works

Fetch a public web page and return only its metadata: title, description, canonical URL, language, site name, author, publish date, image and JSON-LD.

## Output

A JSON object containing the canonical URL, detected language code (e.g. 'en'), page title, and description (or null if not present). No full page body is returned — only structured metadata fields.

## 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": "Public http(s) URL"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com",
  "lang": "en",
  "title": "Example Domain",
  "description": null
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/easy-reader-ai-metadata-endpoint-0665ced9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-reader.gm-tools.workers.dev](https://www.zero.xyz/host/agent-reader.gm-tools.workers.dev/llms.txt)