Use Cradl AI with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Equip your AI agent to extract structured data from any document using Cradl AI's deep learning models.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Complete set · 10 capabilities
The complete Cradl AI capability set.
These are the exact actions your AI can choose when you ask it to work with Cradl AI.
01-04
4 capabilities in this set.
Part of 10 available through Cradl AI.
- 01
Get flow details
Touches integration points and document routing rules boundaries. Get structure and settings for a specific flow
- 02
Get model details
Touches schema definitions, extraction accuracy metrics, and model metadata boundaries. Get details for a specific extraction model
- 03
List extraction models
Resolves model names, versions, and training statuses for document analysis. List all data extraction models in Cradl AI
- 04
Extract data from URL
Touches OCR engine, model prediction, and data normalization boundary. Trigger a new data extraction prediction from a file URL
05-07
3 capabilities in this set.
Part of 10 available through Cradl AI.
- 05
Get batch details
Touches individual file statuses and batch-level processing summary boundaries. Get details for a specific batch of documents
- 06
Get task status
Resolves confidence scores and extracted key-value pairs from the document. Check the status and results of a document task
- 07
List batches
Resolves batch identifiers, creation dates, and total document counts within each batch. List all document batches
08-10
3 capabilities in this set.
Part of 10 available through Cradl AI.
- 08
List processing tasks
Resolves task IDs, statuses (PENDING, COMPLETED, FAILED), and processing timestamps. List recent document processing tasks
- 09
List workflows
Resolves flow IDs, triggers, and configured processing steps. List all document processing flows
- 10
Search models by name
Resolves model metadata based on a name keyword search. Search for extraction models by name
Observed, not estimated
853ms average. Fast in production.
Cradl AI is checked daily against the live service.
- Fastest day
- 766ms
- Slowest day
- 983ms
- 14-day trend
- Improving-21%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Cradl AI, so you can see the experience inside your AI.
It does not authenticate your account with Cradl AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Cradl AI Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_cKCc9rOwoSIb5VyjCclfT9VsRpnAzqU3YLuFHFXM/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Cradl AI capabilities are ready to use.
{
"mcpServers": {
"cradl-ai-mcp": {
"url": "https://edge.vinkius.com/vk_preview_cKCc9rOwoSIb5VyjCclfT9VsRpnAzqU3YLuFHFXM/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
FAQ
Questions Cradl AI owners ask.
- 01
How do I get a Cradl AI API Key?
Log in to your Cradl AI dashboard and navigate to the API section to generate a new key. Ensure you keep this key secure.
- 02
Which document formats are supported?
Cradl AI supports major formats including PDF, JPEG, PNG, and TIFF for data extraction.
- 03
Can I train custom models via chat?
This integration currently focuses on executing extractions and monitoring tasks. Model training should be performed through the Cradl AI dashboard.
Explore
More in Artificial Intelligence
Extracta AI Connector
Automate data extraction via Extracta — process documents into structured JSON, handle AI classification, and
ViewParseur AI Connector
Automate document processing via Parseur — list mailboxes, upload PDFs/Emails, extract structured data pipelin
ViewUnstructured AI Connector
Process and transform complex unstructured data into AI-ready inputs by managing sources, destinations, and wo
ViewiFLYTEK Open Platform / 讯飞开放平台 AI Connector
China's leading voice and NLP platform — convert speech to text, synthesize voice, and analyze text via AI.
View
Suggestions
Alphamoon AI Connector
Extract data from documents using AI-powered OCR and intelligent document processing for contracts, invoices,
ViewFileStack AI Connector
Upload, transform, and analyze files with Filestack—extract text via OCR, detect objects, and manage video tra
ViewDocparser AI Connector
Equip your AI agent to extract data from documents, manage parsers, and track extraction results via the Docpa
ViewMetatext AI Connector
No-code NLP and AI model management via Metatext — run inference and manage datasets.
View
