How to Use the Airparser MCP in Mastra AI

Q: Can Mastra AI handle asynchronous Airparser extraction?

Yes, you can trigger background extraction using parsedocumentasync. Mastra's workflow engine can then poll getdocumentdetails at scheduled intervals until the parsing finishes.

Q: How do I require approval before Mastra AI modifies Airparser webhooks?

Enable requireToolApproval on your Mastra MCP client for the createwebhook and deletewebhook tools. This pauses the workflow and prompts a human operator before any export endpoints are changed.

Build self-healing document extraction workflows in Mastra AI using the Airparser MCP integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airparser MCP to Mastra AI

Create your Vinkius account to connect Airparser 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 Airparser with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fail-Safe Parsing Workflows with Mastra AI

The `parse_document_async` tool kicks off background document extraction while your Mastra AI workflow handles the polling and validation. If the extraction fails or times out, Mastra's built-in engine automatically retries the step with exponential backoff. You design branching logic where Mastra checks the status using `get_document_details`. If the data meets your validation rules, the workflow continues; otherwise, it routes the document to a human reviewer.

Human-Approved Webhooks via Mastra AI

The `create_webhook` tool lets Mastra agents establish automated export targets only after securing explicit human approval. By enabling `requireToolApproval` in your Mastra MCP client, you ensure no external endpoints are registered without a developer's green light. Once approved, the agent runs the tool to link your inbox. If the export destination becomes obsolete, Mastra triggers `delete_webhook` to tear down the bridge automatically.

Strict Schema Validation with Mastra MCP Server

The `get_inbox_schema` tool retrieves the exact JSON structure defined for your document types. Mastra uses this schema to validate extracted data before passing it to downstream APIs or databases. Your agent calls `list_documents` to find pending files, parses them, and checks the results against the schema. If a field is missing, Mastra raises a workflow exception to prevent corrupt data from entering your database.

Setup guide

Set up Airparser 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 Airparser 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: "airparser-mcp-client",
  servers: {
    "airparser-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Airparser 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 Airparser. 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 Airparser 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 Airparser MCP in Mastra AI

Instantiate the MCP client pointing to your Vinkius endpoint, then call `listTools()`. You can spread these tools directly into your Mastra agent definition to give it full parsing capabilities.

Yes, you can trigger background extraction using `parse_document_async`. Mastra's workflow engine can then poll `get_document_details` at scheduled intervals until the parsing finishes.

Enable `requireToolApproval` on your Mastra MCP client for the `create_webhook` and `delete_webhook` tools. This pauses the workflow and prompts a human operator before any export endpoints are changed.

Yes, Mastra automatically detects the transport type, supporting both Server-Sent Events (SSE) and Streamable HTTP. Vinkius manages the connection, so you only need to provide the endpoint URL.

Your PDFs, emails, and images are processed within Airparser's secure parsing engine, returning only structured JSON data to your Mastra host. The connection runs through Vinkius's zero-trust MCP sandbox, meaning no document content is written to persistent logs or shared between client sessions.

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