> ## Documentation Index
> Fetch the complete documentation index at: /docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Assistants connect to Parse over MCP at [https://agent.parse.gl/mcp](https://agent.parse.gl/mcp) (Streamable HTTP). With no sign-in it answers from Parse's public view (the numbers parse.gl's public pages show, up to 5 rows a list), starting with `check_brand`. Signed in with Parse, or sent a workspace key (`parse_mcp_…`), it works in the person's workspace, starting with `get_brief`. Scripts call the same tools over REST at `https://agent.parse.gl/v1/tools/<tool>`.
>
> ```bash
> npx parse-gl init
> ```
>
> To install just the skills: `npx skills add Parsegl/skills`.
> Every tool is also a POST to https://agent.parse.gl/v1/tools/<tool>; its OpenAPI description is https://agent.parse.gl/openapi.json.

# Fetch live pages

> fetch_live_pages: a workspace tool on Parse for agents (agent.parse.gl). Arguments, price, and a call over REST and MCP.

Fetch up to 20 live URLs now as a browser or named AI crawler (GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot) to check HTTP status, robots.txt verdicts, brand mentions, contacts, and JSON-LD (paid: \$0.01/page loaded, runs within monthly budget; quote: true prices without buying). Use only for work the user asked for or pages Parse lacks (never for routine lookups — read\_item reads stored copies free). Robots verdicts, 403/404, and blocked/failed loads are free (notCharged). Identical calls within the UTC hour deduplicate.

## Who may call it, and what it costs

| Name | Access | Effect |
| - | - | - |
| `fetch_live_pages` | A workspace key, or a sign-in that allows changes. | Spends credits, within the budget |

**Price.** \$0.01 a page that loads. A page that does not answer, an HTTP error, a challenge page or a robots.txt verdict is free. `quote: true` prices it only and starts nothing. Every reply says what the call cost in `meta.costCredits`. The prices are on [Spending, tracking and stopping](/docs/credits.md).

## Arguments

**urls** `list of URL` *required*

up to 20

**as** `one of browser, gptbot, oai-searchbot, claudebot, perplexitybot`

browser (default) or a named AI crawler, whose robots.txt rules are obeyed

**brands** `list of string`

brd\_ ids to mark in the text; default the workspace's brands up to 20

**include** `list of one of structuredData`

structuredData: the page's raw JSON-LD blocks, left out unless asked (contacts found in them are always returned) up to 1

**quote** `boolean`

true: the price and whether it fits, buying nothing; without it the call runs when it fits

**idempotencyKey** `string`

the same key with the same arguments returns the same job and charges nothing more; other arguments are refused. Left out, an identical call within the UTC hour is the same call; pass a key to buy it again

Every argument the tool takes, as `GET /v1/tools` serves it, every shared object written out; `https://agent.parse.gl/openapi.json` serves the same schema with the filter and the window named once under `components` and pointed to by `$ref`. MCP `tools/list` leaves out the arguments few calls send, and says the filter and the window once, under `search_answers`; `resolve_ids {"kinds": ["argument"]}` lists what it left out, and a call with any of them runs:

```json theme={null}
{
  "type": "object",
  "properties": {
    "urls": {
      "minItems": 1,
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 2000,
        "format": "uri"
      }
    },
    "as": {
      "description": "browser (default) or a named AI crawler, whose robots.txt rules are obeyed",
      "type": "string",
      "enum": [
        "browser",
        "gptbot",
        "oai-searchbot",
        "claudebot",
        "perplexitybot"
      ]
    },
    "brands": {
      "description": "brd_ ids to mark in the text; default the workspace's brands",
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 3,
        "maxLength": 220
      }
    },
    "include": {
      "description": "structuredData: the page's raw JSON-LD blocks, left out unless asked (contacts found in them are always returned)",
      "maxItems": 1,
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "structuredData"
        ]
      }
    },
    "quote": {
      "description": "true: the price and whether it fits, buying nothing; without it the call runs when it fits",
      "type": "boolean"
    },
    "idempotencyKey": {
      "description": "the same key with the same arguments returns the same job and charges nothing more; other arguments are refused. Left out, an identical call within the UTC hour is the same call; pass a key to buy it again",
      "type": "string",
      "maxLength": 100
    }
  },
  "required": [
    "urls"
  ],
  "additionalProperties": false
}
```

## Example call

Fetch a page as GPTBot sees it, with the robots.txt verdict. Over REST:

```bash theme={null}
export PARSE_API_KEY="<your-key>"

curl -s -X POST https://agent.parse.gl/v1/tools/fetch_live_pages \
  -H 'content-type: application/json' \
  -H "Authorization: Bearer $PARSE_API_KEY" \
  -d '{"urls":["https://acme.com/pricing"],"as":"gptbot"}'
```

Over MCP, the assistant calls the tool by name with the same arguments:

```json theme={null}
{
  "method": "tools/call",
  "params": {
    "name": "fetch_live_pages",
    "arguments": {
      "urls": [
        "https://acme.com/pricing"
      ],
      "as": "gptbot"
    }
  }
}
```

The reply has `data`, `context`, `next`, `page` and `meta`; follow `next` for the calls that come after. A refused call returns `{ code, message, fix }`: see the [error table](/docs/mcp-reference.md#errors).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.