MERCURY Structured Data Extraction API

openapi: 3.2.0
info:
  title: MERCURY x402 storefront Structured Data Extraction API
  version: '1'
  x-spec: mercury-storefront/1
  description: Agent-payable resources over HTTP 402 (x402). LIVE — Base mainnet, real USDC, no token. Only currently-deliverable routes are listed (web-fetch is the live paid SKU; mints are gated off). Free discovery at /.well-known/x402, /x402/discovery, /catalog, and /manifest.
servers:
- url: https://network.mercury-hq.com
tags:
- name: structured-data-extraction
paths:
  /buy/extract:
    get:
      summary: Structured Data Extraction API — URL to typed JSON (schema extract, keyless…
      description: 'TYPED structured extract for autonomous agents — URL + schema → a clean, type-safe JSON record. Where /buy/fetch returns page TEXT (and ?extract= returns string-only fields), THIS returns the schema-conformant object an LLM/RAG/trading pipeline actually consumes: pass ?url=…&schema=title,price:number,rating:number,inStock:boolean and get back { title:"…", price:19.99, rating:4.5, inStock:true } — numbers as numbers, booleans as booleans, absent fields null (honest). `schema` accepts the URL-friendly compact form (field[:type], type in string|number|integer|boolean) OR a Firecrawl/OpenAI-style JSON-Schema object ({"properties":{"price":{"type":"number"}}}). That is Firecrawl''s paid ''JSON mode'' headline guarantee — type-safety, ''numbers as numbers not strings'' — done DETERMINISTICALLY from the page''s own JSON-LD/OpenGraph/meta/microdata: keyless, NO LLM call, NO API key, NO signup, $0.004/call, paid in-band over HTTP 402 (x402, USDC on Base mainnet). The typed record is folded into the SIGNED provenance attestation too (EIP-191, ecrecoverable OFFLINE), so a buyer can prove the EXTRACTED FIELDS — not just raw bytes — are exactly what MERCURY resolved. Honest charge-per-ATTEMPT: every call returns a structured result (success OR an ok:false reason). Same SSRF guard, 5s timeout, 10MB cap, no mint.'
      operationId: buy_extract
      tags:
      - structured-data-extraction
      responses:
        '200':
          description: Delivered after the x402 payment settles on Base mainnet.
          content:
            application/json:
              schema:
                type: object
                properties:
                  ok:
                    type: boolean
                    description: true on success; false on an honest failure (still delivered)
                  url:
                    type: string
                    description: final URL after redirects
                  status:
                    type: integer
                    description: upstream HTTP status
                  extract:
                    type: object
                    description: 'the TYPED record: each requested field resolved + coerced to its declared type (numbers as numbers, booleans as booleans), absent fields null. Deterministic, keyless, no LLM.'
                    additionalProperties:
                      type:
                      - string
                      - number
                      - boolean
                      - 'null'
                  schema:
                    type: object
                    description: echo of the resolved field->type map that was applied
                    additionalProperties:
                      type: string
                  coerced:
                    type: array
                    description: names of the fields that were actually type-cast (present only when non-empty)
                    items:
                      type: string
                  title:
                    type: string
                    description: page <title>
                  text:
                    type: string
                    description: cleaned page text (also returned; markdown if ?format=markdown)
                  bytes:
                    type: integer
                    description: raw body size
                  contentType:
                    type: string
                  truncated:
                    type: boolean
                  redirects:
                    type: array
                    items:
                      type: string
                    description: redirect chain followed
                  fetchedAt:
                    type: string
                    description: ISO timestamp of the fetch (also in the signed attestation)
                  metered:
                    type: boolean
                  delivered:
                    type: string
                  kind:
                    type: string
                  error:
                    type: string
                    description: present only when ok:false
                  attestation:
                    type: object
                    description: EIP-191 provenance receipt over the page text + the typed extract record (canonical key order), ecrecoverable OFFLINE (key at /.well-known/mercury-attestation). Proves the FIELDS are genuine + untampered.
                    properties:
                      keyId:
                        type: string
                      alg:
                        type: string
                      address:
                        type: string
                      contentHash:
                        type: string
                      nonce:
                        type: string
                      signedAt:
                        type: string
                      signature:
                        type: string
                      verify:
                        type: object
                        properties:
                          message:
                            type: string
                          howTo:
                            type: string
                required:
                - ok
                - url
                additionalProperties: false
        '402':
          description: Payment Required — retry with an x402-signed payment (e.g. x402-fetch). Terms are in the challenge body (x402 v1).
      parameters:
      - name: url
        in: query
        required: true
        schema:
          type: string
          maxLength: 2048
          description: the page to extract from (http/https)
        description: the page to extract from (http/https)
      - name: schema
        in: query
        required: true
        schema:
          type: string
          maxLength: 1024
          description: 'fields to extract. COMPACT: comma list of field[:type] (type in string|number|integer|boolean, default string), e.g. title,price:number,rating:number,inStock:boolean. OR a JSON-Schema string ({"properties":{"price":{"type":"number"}}}). Resolved from JSON-LD/OpenGraph/meta/microdata.'
        description: 'fields to extract. COMPACT: comma list of field[:type] (type in string|number|integer|boolean, default string), e.g. title,price:number,rating:number,inStock:boolean. OR a JSON-Schema string ({"properties":{"price":{"type":"number"}}}). Resolved from JSON-LD/OpenGraph/meta/microdata.'
      - name: format
        in: query
        required: false
        schema:
          type: string
          enum:
          - text
          - markdown
          description: 'optional: text (default) or markdown for the page-text field'
        description: 'optional: text (default) or markdown for the page-text field'
      x-payment-info:
        protocols:
        - x402
        scheme: exact
        price: $0.004
        currency: USDC
        network: base
        networkCaip2: eip155:8453
        testnet: false
        asset: '0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913'
        payTo: '0xe10B9d44e72A29B9c19da02981FFCd875308e3C1'
        facilitator: https://api.cdp.coinbase.com/platform/v2/x402
        x402Version: 1
      x-x402:
        scheme: exact
        price: $0.004
        currency: USDC
        network: base
        networkCaip2: eip155:8453
        asset: '0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913'
        payTo: '0xe10B9d44e72A29B9c19da02981FFCd875308e3C1'
        facilitator: https://api.cdp.coinbase.com/platform/v2/x402
        testnet: false
        maxTimeoutSeconds: 60
x-payment-info:
  protocols:
  - x402
  network: base
  currency: USDC
  payTo: '0xe10B9d44e72A29B9c19da02981FFCd875308e3C1'
  facilitator: https://api.cdp.coinbase.com/platform/v2/x402
  testnet: false
  spec: mercury-storefront/1