How to Use the Extracta MCP in Mastra AI

Q: How does Mastra AI handle Extracta extraction failures?

Mastra catches errors from getresults and triggers automatic retries with exponential backoff. This ensures transient network errors do not break your document processing pipeline.

Q: What happens when I call deleteextraction in a workflow?

The deleteextraction tool permanently removes the extraction rules from the MCP server. Any future workflow steps attempting to upload files to that ID will fail immediately.

Build fault-tolerant document workflows with Extracta and Mastra AI using this dedicated 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 Extracta MCP to Mastra AI

Create your Vinkius account to connect Extracta to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build self-healing extraction workflows in Mastra AI

The `upload_file_url` tool integrates into your Mastra AI state machine to initiate document ingestion automatically. If the file host rate-limits the request, Mastra's built-in retry engine backs off and attempts the upload again. Once uploaded, the workflow polls `get_results` to verify the extraction status. If a timeout occurs, the step retries automatically before passing the data to your next workflow node.

Branch workflows based on Extracta classifications

The `create_classification` tool allows your Mastra AI agent to inspect incoming files and sort them into target categories. This setup runs before any data extraction occurs, ensuring files route to the correct processing queue. By reading `get_classification_results`, your workflow branches dynamically. Invoices trigger payment steps, while legal agreements route to a human approval step managed by Mastra's state engine.

Retrieve batch data for Mastra AI background jobs

The `get_batch_results` tool extracts historical data from past document runs to feed your Mastra AI background workers. This allows your agent to analyze trends or rebuild indexes without reprocessing files individually. The agent processes these records sequentially using Mastra's workflow engine. If any batch item fails validation, the workflow isolates the bad record and alerts your admin.

Setup guide

Set up Extracta MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Extracta tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "extracta-mcp-client",
  servers: {
    "extracta-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Extracta Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Extracta tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Extracta transactions"
);
console.log(result.text);

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 Mastra AI

Mastra catches errors from `get_results` and triggers automatic retries with exponential backoff. This ensures transient network errors do not break your document processing pipeline.

Yes, configure your Mastra AI workflow with a tool approval step before calling `create_classification`. The workflow pauses until an admin approves the schema routing.

Initialize the MCP client in Mastra and spread the tools into your agent definition. The agent then calls `create_extraction` to set up the schema before processing documents.

The `delete_extraction` tool permanently removes the extraction rules from the MCP server. Any future workflow steps attempting to upload files to that ID will fail immediately.

Your document URLs and extracted text remain isolated within the Vinkius zero-trust MCP runtime. Extracta processes files ephemerally, ensuring no raw text or classification schemas are stored beyond the lifecycle of your active workflow execution.

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