Amazon Textract is named in the request, but the product page for it was not among the candidates. The closest matches for document text extraction are the community and vendor products below, none of which is Amazon Textract itself; Amazon Textract's own operations (DetectDocumentText, GetDocumentTextDetection, GetDocumentAnalysis) appear only in the action records of a GameLift partner listing 111.
- 1
Amazon Textractamazon.comverified and signed
Amazon Textract's own API operations are DetectDocumentText for synchronous text detection, and GetDocumentTextDetection and GetDocumentAnalysis for retrieving results of asynchronous text detection and analysis 11.
official:API · Amazon Textract+1 community tools built for it
for agents: GetDocumentTextDetection · GetDocumentAnalysis · DetectDocumentText
- 2
LlamaParsellamaindex.aiverified and signed
LlamaParse is an agentic OCR service that parses PDFs, PPTX, DOCX and similar files into text, tables and structured data, with a llamaparse skill for reading documents 15.
+10 community tools built for it
for agents: extract-structured-data-from-unstructured-files-pdf-pptx-docx · liteparse · llamaparse
- 3
Replicate Abiruyt Extract Ocr Textreplicate.comverified and signed
A hosted OCR model that extracts text from an image through Replicate's cloud API 12.
for agents: abiruyt/text-extract-ocr
- 4
Firecrawlfirecrawl.devverified and signed
Firecrawl's firecrawl_parse action parses a supported document into markdown, HTML, links, or JSON matching a schema 14.
official:MCP server · Firecrawl MCP ServerSDK · firecrawl-pyrepository · firecrawlskill · firecrawlskill · firecrawl-search+48 community tools built for it
for agents: scrapeAndExtractFromUrl · extract · firecrawl_parse
- 5
Talonictalonic.comverified and signed
Talonic's Document Extraction action sends a PDF, DOCX, XLSX, image, scan or email and returns schema-validated fields with confidence scores 20.
for agents: Document Extraction · Free Document Tools · Data Delivery
Sources
- 1Dedicated Game Server Hosting | Amazon GameLift Partners | AWSaws.amazon.com · read 2026-10-29
- 2Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 4Firecrawl | Web Data API for AI Agentsfirecrawl.dev · read 2026-10-29
- 5LlamaIndex | AI Agents for Document OCR + Workflowsllamaindex.ai · read 2026-10-29
- 10Talonic · The AI Data Registry for enterprisestalonic.com · read 2026-10-29
- 11Amazon Textract: declares "GetDocumentTextDetection" (the record we read and signed)unfragile.ai · read 2026-10-24
- 12abiruyt/text-extract-ocr: declares "abiruyt/text-extract-ocr" (the record we read and signed)unfragile.ai · read 2026-10-24
- 14Firecrawl API: declares "scrapeAndExtractFromUrl" (the record we read and signed)unfragile.ai · read 2026-10-24
- 15extract-structured-data-from-unstructured-files-pdf-pptx-docx: declares "extract-structured-data-from-unstructured-files-pdf-pptx-docx" (the record we read and signed)unfragile.ai · read 2026-10-24
- 20Talonic: declares "Document Extraction" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
GetDocumentTextDetection · Amazon Textract verified and signed
<p>Gets the results for an Amazon Textract asynchronous operation that detects text in a document. Amazon Textract can detect lines of text and the words that make up a line of text.</p> <p>You start
abiruyt/text-extract-ocr · abiruyt/text-extract-ocr verified and signed
A simple OCR Model that can easily extract text from an image.
extract · extract verified and signed
Extract content from specific URLs using Tavily's extraction API. Returns clean markdown/text from web pages. Use when you have specific URLs and need their content without writing code.
scrapeAndExtractFromUrl · Firecrawl API verified and signed
Hacer scraping de una sola URL y, opcionalmente, extraer información con un LLM
extract-structured-data-from-unstructured-files-pdf-pptx-docx · extract-structured-data-from-unstructured-files-pdf-pptx-docx verified and signed
Invoke this skill BEFORE implementing any structured data extraction from documents to learn the correct llama_cloud_services API usage. Required reading before writing extraction code. Requires llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable.
· aws-lite website read, tools not yet checked
A simple, extremely fast, extensible Node.js client for interacting with AWS services
· Amazon GameLift Partners Boto3 website read, tools not yet checked
If you are looking for services to build and manage game backend features on AWS, we recommend exploring the AWS Partner solutions below that integrate directly with Amazon GameLift.
lucataco/deepseek-ocr · lucataco/deepseek-ocr verified and signed
Convert documents to markdown, extract raw text, and locate specific content
runExtract · DocumentPro (Activepieces) verified and signed
Run Extract — Run an extract/workflow on an uploaded document
aws · aioboto3 verified and signed
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.