Register a free document baseline
fresh402_registerObserves public content without modifying its source. Adds a Fresh402 baseline and uses free registration capacity for new watches; never charges USDC or credits. Use free ($0) Register to save a public HTTPS baseline; no trial key, wallet or payment. Required url plus optional content/attribute rules identifies the watch. Save returned watch_id/hash for Check, Smart Diff or OpenAPI Contract Diff. When flagship workflows are advertised, compatible Website/API workflows accept source_watch_id to adopt this public baseline with its exact rules/time for one separately authorized comparison; it grants no private ownership and performs no extra baseline fetch. Same URL/rules returns existing state without fetching or refreshing; different rules identify another watch. It is not continuous monitoring. HTML/JSON/text only; no JavaScript, private or authenticated targets. DNS/fetch/quota limits apply, including on repeat calls. For walletless first Check inspect root instant_evaluation.enabled and set evaluation:true; separate /v3/agent-trial requires ownership signing. Connection grants no signing or payment authority.
Example tool call
This call uses example arguments supplied in the tool’s input schema.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "https://example.com/docs",
"selector": "main",
"ignore_selectors": [
".timestamp"
]
},
"name": "fresh402_register"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Required absolute public HTTPS document URL, at most 4096 characters, e.g. 'https://example.com/docs'. Only port 443; no embedded credentials, private/local targets or authenticated pages. Fresh402's own service URLs, including its discovery /openapi.json, cannot be targets; choose an external public document. HTML, JSON and plain text are supported; JavaScript is not executed. DNS, redirect and size limits also apply. | |
| selector | No | Optional HTML scope: a supported CSS selector, 1-256 characters, e.g. 'main' or 'article .content'. Only matching text is normalized; no match returns 422. Omit to normalize the page after built-in noise removal. Not supported for JSON or plain text. | |
| html_attributes | No | Optional HTML-only watch rule: up to4 of href,title,alt,aria-label; default[] retains existing text-only normalization. Distinct names are sorted; nonempty rules create a separate version1 watch/baseline. Records bounded meaningful attributes within the saved selector or filtered page, including same-text link destination changes. Cannot be supplied with watch_id, even[]. Unsafe hrefs are hashed, never fetched. Limits:200 elements,2048 characters/value,32768 evidence bytes; excess fails, never clips silently. | |
| ignore_selectors | No | Optional array of up to 20 CSS selectors (each 1-256 characters) to remove from HTML in addition to built-in noise filtering. Default: no extra exclusions ([]). HTML only; use ignore_json_paths for JSON. Example: ['.timestamp', '.ad']. | |
| ignore_json_paths | No | Optional array of up to 20 JSON Pointer-style paths to remove before JSON normalization and hashing. Each must start with '/' and be 1-256 characters; supports '*' segments. Default: [] (no exclusions). JSON only. Example: ['/updated_at', '/items/*/request_id']. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | ||
| hash | No | ||
| note | No | ||
| created | No | ||
| raw_hash | No | ||
| watch_id | No | ||
| final_url | No | ||
| next_step | No | ||
| checked_at | No | ||
| created_at | No | ||
| content_kind | No | ||
| fetch_time_ms | No | ||
| first_seen_at | No | ||
| content_length | No | ||
| html_attributes | No | ||
| baseline_created | No | ||
| workflow_baseline | No | ||
| normalizer_version | No | ||
| snapshot_truncated | No | ||
| html_attribute_rules_version | No |