How to Use the Cradl AI MCP in Cursor

Build document parsing features in Cursor by connecting Cradl AI directly to your codebase.

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 Cursor

Create your Vinkius account to connect Cradl AI to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Draft OCR integration code with live data

Writing document ingestion logic is tedious when you have to guess the API response format. Cursor fixes this by running the MCP tool `extract_data_from_url` on a test file while you are actively coding. The agent sees the exact normalization boundary and writes your parsing functions based on real output. Handling async processing states becomes trivial. Your editor calls `get_task_status` to see the actual confidence scores and key-value pairs Cradl returns. It then generates the exact error handling and retry logic you need for production, using the real JSON structure.

Pull Cradl AI schemas into your Cursor project

Hardcoding field names from a documentation page leads to typos and broken builds. Instead, ask your agent to run `list_extraction_models` and find the exact version you want to target. You get the correct model identifiers injected straight into your environment variables. Generating TypeScript interfaces takes zero manual effort. Cursor uses `get_model_details` to fetch the extraction schema definitions directly from this MCP Server. The AI writes your types using the live metadata, ensuring your code perfectly matches the deployed model.

Debug document workflows inside the editor

Figuring out why a batch failed usually forces you to leave your IDE and dig through logs. Now you can stay in your editor and have the agent run `list_batches` to find the problematic run. It pulls the total document counts and creation dates right into your chat panel. Pinpointing the exact routing error is just one more prompt away. By executing `get_batch_details` and `get_flow_details`, Cursor reads the integration points and file statuses. It can then suggest code fixes for your webhook handlers based on how the flow is actually configured.

Setup guide

Set up Cradl AI MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Cradl AI MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Cradl AI transactions." If the MCP tools are loaded correctly, Cursor will call the Cradl AI tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Create an mcp.json file in your project root or global settings directory. Add the Cradl AI connection details under the mcpServers key. Turn on Agent mode in your chat panel to start calling the tools.

Yes, the agent pulls the exact schema definitions from your account. It reads the fields and data types directly from the model metadata. You get perfectly typed interfaces generated in your current file.

The agent can trigger actual extractions using test URLs you provide. This means it writes parsing logic against real key-value pairs instead of hallucinated mock data. You see exactly how the deep learning models handle your specific files.

Just ask the agent to search your account. It uses the name keyword search tool to find the exact model you need. The correct ID gets pasted right into your configuration file.

Only the specific OCR text and confidence scores requested by the agent enter your editor context. Vinkius manages the MCP connection through an ephemeral, zero-trust architecture. Your raw files remain securely processed within the Cradl infrastructure.

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