How to Use the Affinda MCP in Mastra AI

Q: How do I configure the Affinda MCP Server inside Mastra AI?

Install @mastra/mcp and instantiate the client with your Vinkius endpoint URL. Spread the tools from listTools() directly into your Mastra agent configuration.

Q: Can Mastra AI retry failed Affinda document uploads?

Yes, Mastra's workflow engine automatically retries the createdocument tool if it encounters a network timeout. You can configure the exact backoff intervals in your workflow definition.

Q: How do Mastra AI agents use Affinda workspace data over MCP?

The agent calls listworkspaces to find the correct destination container. It then uses that workspace ID to organize and query documents during execution.

Q: Is human-in-the-loop approval supported for document processing?

Yes, you can use Mastra's requireToolApproval flag on the parsing tools. This pauses the workflow until a human reviews the extracted invoice or resume data.

Build resilient document workflows that parse resumes and invoices using Mastra AI and the Affinda 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 Affinda MCP to Mastra AI

Create your Vinkius account to connect Affinda 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 Affinda with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated document routing in Mastra workflows

The `create_document` tool integrates directly into Mastra AI's workflow engine to handle incoming files. If a document fails to parse, Mastra's built-in retry logic kicks in with exponential backoff. This MCP Server setup ensures that every resume or invoice gets processed even during temporary API hiccups. You write the routing logic once, and Mastra handles the execution path.

Conditional branching for invoice validation

The `get_document` tool retrieves the parsed JSON data so your Mastra AI agent can run conditional checks. If the invoice total exceeds a threshold, the workflow branches to trigger an admin notification. You can combine this with `list_workspaces` to make sure documents are sorted into the correct container based on their parsed metadata. The workflow engine manages the state transitions automatically.

Dynamic schema matching with Mastra agents

The `list_document_types` tool lets your Mastra AI agent inspect which parsing models are available over the MCP connection before submitting a file. The agent selects the correct model—like passport or invoice—based on the file extension or metadata. Then, `list_documents` checks the workspace to make sure no duplicate files are processed. This keeps your document pipelines clean and prevents double-billing on your parsing API.

Setup guide

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

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

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

Install `@mastra/mcp` and instantiate the client with your Vinkius endpoint URL. Spread the tools from `listTools()` directly into your Mastra agent configuration.

Yes, Mastra's workflow engine automatically retries the `create_document` tool if it encounters a network timeout. You can configure the exact backoff intervals in your workflow definition.

The agent calls `list_workspaces` to find the correct destination container. It then uses that workspace ID to organize and query documents during execution.

Yes, you can use Mastra's `requireToolApproval` flag on the parsing tools. This pauses the workflow until a human reviews the extracted invoice or resume data.

Your PDF invoices and ID images are sent directly to the secure API via the Vinkius sandbox. No document payloads are stored on Vinkius, maintaining strict data isolation for your parsed files.

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