Contrie

Extract structured data from one public web page. Describe the fields you want in natural language and/or pass a JSON Schema for the exact shape. Returns JSON plus metadata you can branch on: qualityScore (0-100; structured acceptance also requires success and valid), grounding (value presence, not field attribution), high-level progress and credits charged. Also returns groundingFields, a per-field grounding verdict with page excerpts, so you can see which extracted values have matching source text; this does not establish factual truth or correct field association. Requires authentication: sign in with your Contrie account (OAuth), or send an API key in the Authorization header. Exact recorded URL-and-prompt requests listed in /llms.txt work without either. Not a crawler or a search engine: one page per call. Eligible JavaScript shells can use bounded browser rendering; successful rendered answers add 2 credits.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "The public web page to extract from"
    },
    "extract": {
      "description": "What to extract, in natural language (e.g. \"product name, price, and stock status\")",
      "type": "string",
      "maxLength": 4000
    },
    "schema": {
      "description": "JSON Schema subset, max 10,000 serialized UTF-8 bytes: object/array/string/number/integer/boolean, properties, required, items, enum",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "idempotencyKey": {
      "description": "Stable request ID, 8–200 visible ASCII characters. Reuse the same ID and inputs to recover a completed response for 24 hours without another extraction or charge. Use a new ID for deliberately new work. Requires authentication.",
      "type": "string",
      "pattern": "^[\\x21-\\x7e]{8,200}$"
    },
    "maxAge": {
      "description": "Accept page bytes from your account fetched up to this many seconds ago; origin expiry may be shorter. Default 0 bypasses cache reads/writes. Query/fragment/user-info URLs and restricted origin responses are never cached.",
      "type": "integer",
      "minimum": 0,
      "maximum": 86400
    },
    "render": {
      "description": "auto (default): render in a browser only if the page is a JavaScript shell; always: render first; never: plain fetch only. Rendering adds 2 credits.",
      "type": "string",
      "enum": [
        "auto",
        "always",
        "never"
      ]
    }
  },
  "required": [
    "url"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Read one public web page as clean, structure-preserving markdown (headings, lists, tables, links) with common page boilerplate removed where recognized. The call costs 1 credit before any requested rendering. Returns the full REST-shaped JSON response in this tool's text content: data is null, markdown holds the page, and metadata includes credits and evidence status. Use this when you just need to read a page; use contrie_extract when you need typed fields. Requires authentication: sign in with your Contrie account (OAuth), or send an API key in the Authorization header. Eligible JavaScript shells can use bounded browser rendering; successful rendered reads add 2 credits.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "The public web page to read"
    },
    "idempotencyKey": {
      "description": "Stable request ID, 8–200 visible ASCII characters. Reuse the same ID and inputs to recover a completed response for 24 hours without another extraction or charge. Use a new ID for deliberately new work. Requires authentication.",
      "type": "string",
      "pattern": "^[\\x21-\\x7e]{8,200}$"
    },
    "maxAge": {
      "description": "Accept page bytes from your account fetched up to this many seconds ago; origin expiry may be shorter. Default 0 bypasses cache reads/writes. Query/fragment/user-info URLs and restricted origin responses are never cached.",
      "type": "integer",
      "minimum": 0,
      "maximum": 86400
    },
    "render": {
      "description": "auto (default): render in a browser only if the page is a JavaScript shell; always: render first; never: plain fetch only. Rendering adds 2 credits.",
      "type": "string",
      "enum": [
        "auto",
        "always",
        "never"
      ]
    }
  },
  "required": [
    "url"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Read your own account’s used, reserved and unreserved included credits, next allowance reset and current restrictions. Costs zero extraction credits and reserves no capacity. Eligibility is advisory: source, service and request-specific checks still apply. Requires account authorization. Call before first or repeat work, not in a polling loop.

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Check data you already have against the page it claims to come from, field by field. Takes extracted data from ANY source — another tool, your own scrape, a stored record — plus a url (or raw html/text) and reports which values actually appear in the source and which do not, with a supporting excerpt for each. This check charges no credits. Requires authentication: sign in with your Contrie account (OAuth), or send an API key in the Authorization header. It answers "is this value present in this page", NOT "does the page say this about that": a value that is correct for a different field still reads as grounded. Use it to bound invention before you act on data you did not verify yourself.

{
  "type": "object",
  "properties": {
    "data": {
      "description": "The extracted data to check, as a JSON object or array"
    },
    "url": {
      "description": "The page the data claims to come from; omit if passing html or text",
      "type": "string",
      "format": "uri"
    },
    "html": {
      "description": "Raw HTML of the source, max 5,000,000 UTF-8 bytes",
      "type": "string",
      "maxLength": 5000000
    },
    "baseUrl": {
      "description": "With html only: the page it came from, to resolve relative links; never fetched",
      "type": "string",
      "format": "uri"
    },
    "text": {
      "description": "Plain text of the source, max 5,000,000 UTF-8 bytes",
      "type": "string",
      "maxLength": 5000000
    }
  },
  "required": [
    "data"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Watch one public web page for one question and be told when the answer changes. Runs the extraction now as a baseline, then on a schedule with `every` minutes between slots (minimum 15); delayed or missed slots can occur. On a change Contrie records the before and after responses and their evidence status plus a field diff, readable with contrie_changes, and attempts one POST to webhookUrl if given (signed X-Contrie-Signature; the secret is returned once). Every run with an accepted answer, the baseline included, is charged like one extraction (1, 3, 8 or 15 credits, plus 2 when rendered), so an hourly monitor can make up to 24 charged runs a day until you stop it. Stop it with contrie_unwatch; list yours with contrie_monitors. Requires authentication: sign in with your Contrie account (OAuth), or send an API key in the Authorization header.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "The public page to watch"
    },
    "extract": {
      "description": "What to watch, in plain language",
      "type": "string",
      "maxLength": 4000
    },
    "schema": {
      "description": "JSON Schema of the answer, max 10,000 serialized UTF-8 bytes",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "every": {
      "description": "Minutes between scheduled slots (default 60); delays or missed slots can occur",
      "type": "integer",
      "minimum": 15,
      "maximum": 10080
    },
    "webhookUrl": {
      "description": "https URL to POST changes to",
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "url"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Read a monitor's history: its latest answer with evidence status and the last 20 events (baseline, change, error). Every change carries the full before and after responses with evidence, and a diff of the fields that moved. Charges no credits. Requires authentication: sign in with your Contrie account (OAuth), or send an API key in the Authorization header.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "The monitor id from contrie_watch"
    }
  },
  "required": [
    "id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

List your active monitors: id, url, question, cadence, next scheduled run and latest answer. Stopped monitors are not listed; their history stays readable with contrie_changes. Charges no credits. Requires authentication: sign in with your Contrie account (OAuth), or send an API key in the Authorization header.

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Stop one of your monitors so it makes no further scheduled runs and no further charges; a run already in progress can still finish and be charged. History stays readable with contrie_changes. Returns the monitor with active: false; stopping an already stopped monitor returns it unchanged. A stopped monitor cannot be restarted: create a new one with contrie_watch. Charges no credits. Requires authentication: sign in with your Contrie account (OAuth), or send an API key in the Authorization header.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "The monitor id from contrie_watch or contrie_monitors"
    }
  },
  "required": [
    "id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}