How to Use the Extracta MCP in Claude

Q: How do I connect the Extracta MCP Server to Claude Desktop?

Open your claudedesktopconfig.json file through the developer settings. Add the server details under the mcpServers key with your Vinkius credentials, then restart the app.

Q: Can I process local files using Extracta in Claude Desktop?

No, the uploadfileurl tool requires a publicly accessible URL. You can upload files to a temporary cloud storage bucket first, then pass that URL to your agent in the chat.

Q: How does Claude Desktop handle long document processing times with Extracta?

Your agent uses getresults to poll the status of your document. If the extraction isn't finished yet, the tool returns a processing status, and the agent waits a few seconds before checking again.

Get clean, structured JSON from any document URL directly inside Claude Desktop without writing a single line of code.

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 Claude Desktop

Create your Vinkius account to connect Extracta 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 Extracta with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Parse raw documents into structured JSON

The `create_extraction` tool lets your agent define the exact schema, language, and fields you need to pull from your documents. You tell your agent what fields matter—like invoice dates or total amounts—and it configures the extraction pipeline instantly. Once configured, use `upload_file_url` to feed document links directly into Claude Desktop. Your agent then uses `get_results` to poll the status and spit out structured data right in your chat window.

Classify files automatically with this MCP Server

This MCP server's `create_classification` tool sets up automated document sorting by analyzing files against your custom JSON schemas. If you deal with a mix of invoices, contracts, and receipts, this tool tells your agent how to organize them. Your agent calls `get_classification_results` to instantly identify what kind of document just arrived. You can audit these settings anytime using `view_classification` to make sure your sorting rules stay accurate.

Manage and audit extraction configurations

The `update_extraction` tool lets you modify your existing field mappings on the fly without breaking your setup. If you need to add a new field to your extraction template, your agent handles the update directly in your workspace using this MCP connection. You can clean up old configurations using `delete_extraction` when a project wraps up. To review past work, your agent calls `get_batch_results` to pull bulk historical data for quick audits.

Setup guide

Set up Extracta 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 Extracta 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 Extracta 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 extracta-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 Claude Desktop

Open your `claude_desktop_config.json` file through the developer settings. Add the server details under the `mcpServers` key with your Vinkius credentials, then restart the app.

No, the `upload_file_url` tool requires a publicly accessible URL. You can upload files to a temporary cloud storage bucket first, then pass that URL to your agent in the chat.

Your agent uses `get_results` to poll the status of your document. If the extraction isn't finished yet, the tool returns a processing status, and the agent waits a few seconds before checking again.

Yes. You don't need to build a new pipeline from scratch. Just tell your agent to use `update_extraction` to modify your existing mapping rules on the fly.

Your document URLs and the extracted JSON data are processed through Vinkius's secure sandboxed environment. No files are stored permanently on Vinkius servers, and your API credentials remain encrypted.

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