Read a Hacker News thread as JSON.

curl "https://getjson.de/https://news.ycombinator.com/item?id=1"

{
  "source": {
    "url": "https://news.ycombinator.com/item?id=1",
    "finalUrl": "https://news.ycombinator.com/item?id=1",
    "kind": "thread",
    "platform": "hackernews",
    "provider": "hackernews",
    "fetchedAt": "2026-10-27T21:23:57.042Z",
    "cached": false
  },
  "content": {
    "title": "Y Combinator",
    "author": {
      "name": "pg",
      "handle": "pg",
      "url": "https://news.ycombinator.com/user?id=pg"
    },
    "publishedDate": "2006-10-09T18:21:51.000Z",
    "language": null,
    "engagement": {
      "points": 57,
      "comments": 3
    },
    "hashtags": [],
    "mentions": [],
    "linkedContent": [
      {
        "type": "link",
        "url": "http://ycombinator.com"
      }
    ],
    "truncated": false,
    "text": "## Comments\n\n- **sama**: \"the rising star of venture capital\" -unknown VC eating lunch on SHR\n  - **pg**: Is there anywhere to eat on Sandhill Road?\n    - **dmon**: sure",
    "wordCount": 29
  },
  "meta": null,
  "wall": null,
  "result": null
}

Recorded from https://getjson.de on 2026-10-27 with no key. Long text is cut and ends in " …".

• The provider is hackernews: the HN API for the item, HN search (Algolia) for the comments.
• kind is thread with up to 200 comments in 4 levels, or post for an item without comments.
• Put the link in quotes in a shell, because of the ?.

curl -G https://getjson.de/https://news.ycombinator.com/item?id=1 --data-urlencode 'schema={"type":"object","properties":{"commenters":{"type":"array","items":{"type":"string"}}}}'

Without a key a network has 3 schema calls a day. The call waits up to 60 s and fills result, validated against the schema. No answer of this call is recorded on this page.

The MCP tool read needs no key. Connect, then call it:

claude mcp add --transport http getjson https://getjson.de/mcp

{
  "name": "read",
  "arguments": {
    "url": "https://news.ycombinator.com/item?id=1"
  }
}

The tool answers with the same envelope as text.

getJSON reads any content a user or an agent points at, a web page or a file, and returns JSON in your schema, validated. Try and use it without an account. Guide for agents