Firecrawl · Capability

Firecrawl API — Extraction

Firecrawl API — Extraction. 2 operations. Lead operation: Extract structured data from pages using LLMs. Self-contained Naftiko capability covering one Firecrawl business surface.

Run with Naftiko FirecrawlExtraction

What You Can Do

POST
Extractdata — Extract structured data from pages using LLMs
/v1/extract
GET
Getextractstatus — Get the status of an extract job
/v1/extract/{id}

MCP Tools

extract-structured-data-pages-using

Extract structured data from pages using LLMs

get-status-extract-job

Get the status of an extract job

read-only idempotent

Capability Spec

firecrawl-extraction.yaml Raw ↑
naftiko: 1.0.0-alpha2
info:
  label: Firecrawl API — Extraction
  description: 'Firecrawl API — Extraction. 2 operations. Lead operation: Extract structured data from pages using LLMs. Self-contained
    Naftiko capability covering one Firecrawl business surface.'
  tags:
  - Firecrawl
  - Extraction
  created: '2026-05-19'
  modified: '2026-05-19'
binds:
- namespace: env
  keys:
    FIRECRAWL_API_KEY: FIRECRAWL_API_KEY
capability:
  consumes:
  - type: http
    namespace: firecrawl-extraction
    baseUri: https://api.firecrawl.dev/v2
    description: Firecrawl API — Extraction business capability. Self-contained, no shared references.
    resources:
    - name: extract
      path: /extract
      operations:
      - name: extractdata
        method: POST
        description: Extract structured data from pages using LLMs
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    - name: extract-id
      path: /extract/{id}
      operations:
      - name: getextractstatus
        method: GET
        description: Get the status of an extract job
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
    authentication:
      type: bearer
      token: '{{env.FIRECRAWL_API_KEY}}'
  exposes:
  - type: rest
    namespace: firecrawl-extraction-rest
    port: 8080
    description: REST adapter for Firecrawl API — Extraction. One Spectral-compliant resource per consumed operation, prefixed
      with /v1.
    resources:
    - path: /v1/extract
      name: extract
      description: REST surface for extract.
      operations:
      - method: POST
        name: extractdata
        description: Extract structured data from pages using LLMs
        call: firecrawl-extraction.extractdata
        with:
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/extract/{id}
      name: extract-id
      description: REST surface for extract-id.
      operations:
      - method: GET
        name: getextractstatus
        description: Get the status of an extract job
        call: firecrawl-extraction.getextractstatus
        outputParameters:
        - type: object
          mapping: $.
  - type: mcp
    namespace: firecrawl-extraction-mcp
    port: 9090
    transport: http
    description: MCP adapter for Firecrawl API — Extraction. One tool per consumed operation, routed inline through this capability's
      consumes block.
    tools:
    - name: extract-structured-data-pages-using
      description: Extract structured data from pages using LLMs
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: firecrawl-extraction.extractdata
      with:
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: get-status-extract-job
      description: Get the status of an extract job
      hints:
        readOnly: true
        destructive: false
        idempotent: true
      call: firecrawl-extraction.getextractstatus
      outputParameters:
      - type: object
        mapping: $.