Cradl AI Connector for AI agents.
10 live capabilities
Automate document data extraction from invoices, IDs, and custom forms.
Waiting for input…
Why people use Cradl AI
Cradl AI Document Extraction for High-Volume Finance Workflows
With Cradl AI, your agent handles the extraction. You just give it a URL. It identifies the fields, pulls the data, and presents it to you. You get a clean data set instead of a messy file.
What Vinkius changes
You turn messy PDFs into clean data without clicking a single button.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Automated Invoice Processing
A finance lead asks the agent to pull totals from a pile of PDF invoices.
- Real-world use case 02
ID Verification Workflows
A security admin needs to check IDs.
- Real-world use case 03
Batch Receipt Auditing
An ops manager wants to know how many receipts were processed today.
Complete set · 10capabilities
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 Capability
Get batch details
Get details for a specific batch of documents. Use this to see the summary of a large group of files.
- 02 Capability
Get flow details
Get structure and settings for a specific flow. This helps you understand how documents are routed through your system.
- 03 Capability
Get model details
Get details for a specific extraction model. Use this to see accuracy metrics and metadata for your models.
- 04 Capability
Get task status
Check the status and results of a document task. This tells you if a specific file was processed and what the confidence score was.
05—07
3 capabilities in this set.
Part of 10 available through Cradl AI.
- 05 Capability
List batches
List all document batches. Use this to see all your processed groups and their total document counts.
- 06 Capability
List extraction models
List all data extraction models in Cradl AI. Use this to see which models are trained and ready for use.
- 07 Capability
List processing tasks
List recent document processing tasks. This gives you a quick view of all pending, completed, or failed tasks.
08—10
3 capabilities in this set.
Part of 10 available through Cradl AI.
- 08 Capability
Search models by name
Search for extraction models by name. This helps you find specific models quickly in a large library.
- 09 Capability
Extract data from url
Trigger a new data extraction prediction from a file URL. This lets your agent pull data from a link instantly.
- 10 Capability
List workflows
List all document processing flows. This lets you see all your configured triggers and processing steps.
Set up in minutes
One URL. Then ask Cradl AI to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Cradl AI from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_cKCc9rOwoSIb5VyjCclfT9VsRpnAzqU3YLuFHFXM/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Cradl AI, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Cradl AI for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_cKCc9rOwoSIb5VyjCclfT9VsRpnAzqU3YLuFHFXM/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Cradl AI URL.
- Step 03
Save and start
Save the connection and enable Cradl AI in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"cradl-ai": {
"url": "https://edge.vinkius.com/vk_preview_cKCc9rOwoSIb5VyjCclfT9VsRpnAzqU3YLuFHFXM/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Cradl AI
Open Agent mode in chat and ask: "Using Cradl AI, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"cradl-ai": {
"url": "https://edge.vinkius.com/vk_preview_cKCc9rOwoSIb5VyjCclfT9VsRpnAzqU3YLuFHFXM/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Cradl AI
Ask Copilot: "Using Cradl AI, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"cradl-ai": {
"url": "https://edge.vinkius.com/vk_preview_cKCc9rOwoSIb5VyjCclfT9VsRpnAzqU3YLuFHFXM/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Cradl AI
Open Cascade and ask: "Using Cradl AI, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"cradl-ai": {
"url": "https://edge.vinkius.com/vk_preview_cKCc9rOwoSIb5VyjCclfT9VsRpnAzqU3YLuFHFXM/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Cradl AI
Ask Cline: "Using Cradl AI, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add cradl-ai --transport http "https://edge.vinkius.com/vk_preview_cKCc9rOwoSIb5VyjCclfT9VsRpnAzqU3YLuFHFXM/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Cradl AI
Ask Claude: "Using Cradl AI, show me...". 10 tools are ready
Where the request belongs
Work Cradl AI can move forward.
This is for the finance manager drowning in receipts, the ops lead trying to scale document intake, or the dev building a custom automated pipeline. You need to get rid of manual data entry and trust your automated outputs.
Finance Clerk
Processes hundreds of invoices a day and needs to eliminate manual typing.
Operations Manager
Monitors high-volume document flows to ensure accuracy across departments.
Backend Developer
Integrates document processing into an app and needs to audit model performance.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsSensible
Extract structured data from PDFs, images, and documents using Sensible's powerful document parsing engine.
AlgoDocs
AI document extraction orchestration. parse PDFs, images, and Word docs via AI.
Docparser
Equip your AI agent to extract data from documents, manage parsers, and track extraction results via the Docparser API.
Extracta
Automate data extraction via Extracta. process documents into structured JSON, handle AI classification, and audit extraction history directly from any AI agent.
Alphamoon
Extract data from documents using AI-powered OCR and intelligent document processing for contracts, invoices, and forms.
Parsio
Extract structured data from emails and PDFs automatically with AI-powered parsing templates that learn from your documents.
Bring your own AI
Change the model, client or framework. Keep Cradl AI connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Cradl AI.
The practical details behind the request, access and result.
What can Cradl AI do for my business?
It extracts structured data from documents like invoices and IDs so you don't have to type it in manually.
Can Cradl AI handle different types of documents?
Yes, it works on invoices, receipts, IDs, and even your own custom forms.
How does Cradl AI improve my data accuracy?
It uses deep learning to identify fields and provides confidence scores so you know the data is reliable.
Can I use Cradl AI to process documents in bulk?
Yes, you can use it to handle entire batches of documents at once and get a summary of the results.
How do I connect Cradl AI to my AI agent?
You just need your API key from the Cradl AI dashboard to link it to your client.
Does Cradl AI work with my custom forms?
Yes, it supports custom-trained models so you can extract data from your specific company documents.
Can I see the progress of my document processing?
Yes, you can check the status of individual tasks or see the summary of entire batches in real-time.
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.
Which document formats are supported?
Cradl AI supports major formats including PDF, JPEG, PNG, and TIFF for data extraction.
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.
One connection away
Give your agent a direct line to Cradl AI.
Connect Cradl AI once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available