How to Use the Cradl AI MCP in Claude Code

Q: What is the command to install the Cradl AI MCP Server in Claude Code?

Run claude mcp add --transport http cradl-ai -- . Make sure all your transport and header flags come before the server name.

Pipe Cradl AI extractions directly into your terminal workflows using Claude Code and this headless MCP Server.

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 Code

Create your Vinkius account to connect Cradl AI to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Extractions from the Command Line

The `extract_data_from_url` tool allows Claude Code to pass file URLs to the OCR engine right from your shell. You can script a daily cron job that feeds new invoices into the prediction model automatically. Checking the output happens through the `get_task_status` tool. Your headless script polls the endpoint, retrieves the extracted key-value pairs, and pipes the structured JSON into your backend systems.

Audit Cradl AI Batch Jobs via Terminal

Monitoring high-volume processing is simple when you call `list_batches` to grab identifiers and document counts. You get a clear view of your queue without ever opening a web dashboard. When a script needs to verify completion, it runs `get_batch_details` alongside `list_processing_tasks`. This combination exposes the exact processing timestamps and isolates any failed files in the run.

Query MCP Server Models and Schemas

Your terminal agent discovers available parsers by executing `list_extraction_models`. It pulls down model names and versions so your deployment scripts know which targets are active. For detailed inspection, Claude Code uses `get_model_details` to fetch schema definitions and extraction accuracy metrics. This guarantees your database migrations match the exact fields the model outputs.

Setup guide

Set up Cradl AI MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see cradl-ai-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Cradl AI transactions." It will automatically discover and invoke the available Cradl AI tools.

Terminal

claude mcp add --transport http cradl-ai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Cradl AI MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "cradl-ai-mcp": {
      "type": "url",
      "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 Code

Run `claude mcp add --transport http cradl-ai -- `. Make sure all your transport and header flags come before the server name.

Yes, you can script this for CI/CD. The terminal agent runs headless, triggering document extractions and validating the results during your build process.

Ask the CLI to list recent processing tasks. It will query the endpoint and print out any jobs marked with a FAILED status along with their timestamps.

Yes, it uses the built-in search tool to find models by name keyword. You get the metadata returned directly to your standard output.

Your terminal only exchanges file URLs and extracted schema fields with the zero-trust Vinkius endpoint. No document content is stored permanently, and the connection drops as soon as your script exits.

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