How to Use the Cradl AI MCP in Claude

Connect Cradl AI to Claude Desktop to extract structured data from documents directly in your chat window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cradl AI MCP to Claude Desktop

Create your Vinkius account to connect Cradl AI to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Cradl AI with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run OCR and extract data via Claude Desktop

Drop a document link into your chat and watch your agent pull the exact fields you need. You do not have to write custom parsing logic or deal with messy PDF layouts. The `extract_data_from_url` tool tells Cradl AI to grab the file, run its deep learning models, and normalize the output. Getting the results is just as fast. Claude uses `get_task_status` to fetch the extracted key-value pairs alongside their confidence scores. If a field looks questionable, you see the low confidence metric immediately and can ask your agent to double-check the raw text.

Inspect extraction schemas and model metrics

Knowing what a model expects saves hours of debugging. When you ask Claude to check your MCP setup, it calls `list_extraction_models` to see every trained model available in your account. You get version numbers and training statuses without leaving the conversation. Digging deeper requires specific metadata. Running `get_model_details` pulls the exact schema definitions and historical accuracy metrics for any chosen model. Your AI client knows exactly which fields it should look for before it even touches a document.

Track document batches across this MCP Server

Managing bulk document processing usually means staring at a dashboard. Now you can just ask Claude how the monthly invoice run is doing. The `list_batches` command grabs the batch identifiers and total document counts instantly. Tracking individual failures takes seconds. By running `get_batch_details`, your agent checks the processing summary and flags any files that got stuck. If you need to understand why a document routed a certain way, `get_flow_details` exposes the underlying integration points and routing rules.

Setup guide

Set up Cradl AI MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Cradl AI MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Cradl AI MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under cradl-ai-mcp.

json

{
  "mcpServers": {
    "cradl-ai-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Cradl AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Cradl AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Cradl AI MCP in Claude Desktop

Open your Claude Desktop settings and click Developer to edit the configuration file. Add the Cradl AI server command to your mcpServers block and restart the app. You can also paste the remote URL directly into Claude Web under the Integrations menu.

Yes, your agent can start new jobs right from the prompt. It uses the file URL you provide to kick off the prediction process. You get the structured output back in the chat once the task finishes.

Your agent will catch the error automatically. It runs the status check tool to see if the state is PENDING, COMPLETED, or FAILED. From there, it can tell you exactly which document caused the issue.

Any model you train in your Cradl account is accessible here. The search tool lets you find specific custom models by name. You can then pull their schemas to see exactly what fields they extract.

This MCP server only processes the specific file URLs and extracted key-value pairs you explicitly send through it. Cradl AI runs in a zero-trust, ephemeral V8 isolate sandbox on Vinkius. Your raw document text never leaks into unauthorized storage.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript