How to Use the Extracta MCP in Cursor

Q: How do I configure the Extracta MCP Server in Cursor?

Add the server configuration to your global /.cursor/mcp.json file or a project-specific .cursor/mcp.json file. Once saved, enable Agent mode in your Cursor chat to start calling the tools.

Q: Can Cursor automatically write parser code using Extracta?

Yes. Your agent can run getresults to see the exact JSON structure returned from a document, then generate precise parser functions or TypeScript types based on that live output.

Q: How do I debug failing document uploads in Cursor with Extracta?

Ask your agent to run viewextraction to check your configuration. If the setup is correct, verify that the URL passed to uploadfileurl is publicly accessible and not blocked by a firewall.

Q: How do I pull historical extraction data for testing?

You can use the getbatchresults tool. This lets your agent retrieve bulk historical data from your extraction process so you can test your local code against real past results.

Feed structured document data directly into your active codebase using Extracta inside Cursor's Agent mode.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Extracta MCP to Cursor

Create your Vinkius account to connect Extracta 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 Extracta with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate typed code from real document schemas

The `create_extraction` tool lets your agent define document schemas and instantly receive an extraction ID. Instead of writing mock data, Cursor uses this ID to pull real structured JSON directly into your editor. By calling `upload_file_url` and tracking it with `get_results`, the agent gets actual payloads to build your TypeScript interfaces or Python models. You write your application code against live data structures, not guesses.

Route files using the Extracta MCP Server

The `create_classification` tool allows Cursor to set up intelligent document routing rules directly inside your development environment. You provide a JSON schema of target categories like receipts or contracts. This MCP toolset lets your agent call `get_classification_results` to determine file types on the fly. This lets you write and test file-routing scripts with real-time classification feedback from the server.

Keep your extraction pipelines updated

The `update_extraction` tool lets you modify mapping rules directly from your workspace using this MCP server. If a client changes their invoice format, you don't have to write a new integration. Your agent calls `view_extraction` to inspect the current setup, applies the necessary changes, and verifies them. You can also clean up stale pipelines using `delete_extraction` to keep your environment tidy.

Setup guide

Set up Extracta 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 Extracta 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 Extracta transactions." If the MCP tools are loaded correctly, Cursor will call the Extracta tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "extracta-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 Extracta. 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 Extracta 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 Extracta MCP in Cursor

Add the server configuration to your global `~/.cursor/mcp.json` file or a project-specific `.cursor/mcp.json` file. Once saved, enable Agent mode in your Cursor chat to start calling the tools.

Yes. Your agent can run `get_results` to see the exact JSON structure returned from a document, then generate precise parser functions or TypeScript types based on that live output.

Ask your agent to run `view_extraction` to check your configuration. If the setup is correct, verify that the URL passed to `upload_file_url` is publicly accessible and not blocked by a firewall.

You can use the `get_batch_results` tool. This lets your agent retrieve bulk historical data from your extraction process so you can test your local code against real past results.

Yes. Your JSON schemas, classification rules, and document URLs are transmitted securely via HTTPS. All operations run in an isolated environment, ensuring your proprietary code and data schemas never leak.

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