How to Use the Cradl AI MCP in VS Code Copilot

Deploy Cradl AI to your entire engineering team by adding this MCP Server to VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect Cradl AI to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Test document extraction inside VS Code Copilot

Building integrations for document processing requires constant testing against real API responses. Copilot handles this by executing `extract_data_from_url` directly from your prompt. Your team gets immediate feedback on how the OCR engine normalizes specific file formats. Verifying the results happens without leaving your split view. The agent calls `get_task_status` to retrieve the extracted key-value pairs and their associated confidence scores. Engineers can write validation logic based on actual prediction data instead of guessing what the API might return.

Share Cradl AI schemas across your team

Keeping a team of developers synced on data schemas is notoriously difficult. By committing your tool configuration to the repository, every developer can run `list_extraction_models` to see the current training statuses. Nobody has to hunt down the latest documentation page. Mapping those schemas into your codebase is completely automated. Copilot uses `get_model_details` to pull the exact extraction accuracy metrics and schema definitions from this MCP Server. Your engineers get identical, accurate data structures generated right in their active editor tabs.

Monitor processing tasks from the editor

Production issues often require checking batch statuses quickly. Instead of logging into a separate web portal, developers can ask Copilot to trigger `list_batches`. The agent fetches the batch identifiers and total document counts instantly. Diagnosing a stuck pipeline takes a fraction of the time. Running `get_batch_details` reveals individual file statuses, while `list_processing_tasks` shows the exact processing timestamps. If a document routes incorrectly, `get_flow_details` exposes the specific routing rules causing the problem.

Setup guide

Set up Cradl AI MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Cradl AI MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Cradl AI tools listed. Try asking: "List my recent Cradl AI transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Create a .vscode/mcp.json file in your project root and add the Cradl AI connection block. Commit this file to your Git repository. Every developer opening the project will instantly have access to these tools in their chat panel.

Yes, the agent can pull historical accuracy data for any of your models. It reads the model metadata to help you decide which version to use in your code. This ensures your team builds against the most reliable extraction schemas.

Your developers can ask the agent to check the recent processing tasks. It will list the failed task IDs and their timestamps. They can then pull the flow details to see if a routing rule caused the error.

No additional extensions are necessary if you are running version 1.96 or higher. The built-in agent mode handles the connection natively. The shared configuration file ensures uniform access across the entire engineering department.

The integration only accesses the specific flow configurations and normalized document data requested during your coding sessions. Vinkius secures the traffic through an ephemeral V8 sandbox that requires zero inbound firewall changes. Your organization's raw files are never stored in the editor context.

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