How to Use the Finch MCP in Mastra AI

Automate complex HR workflows in Mastra AI with conditional logic and built-in error handling for your payroll operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Finch MCP to Mastra AI

Create your Vinkius account to connect Finch 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 Finch with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step HR automation

Chain your payroll tasks together. Use `list_automated_jobs` to monitor sync status, then trigger follow-up actions if a record fails to update. Your agent handles the branching logic. If one tool call fails, you can define a fallback path to retry or log an alert for the admin.

Conditional payroll branching

Build logic based on live pay data. You can inspect `list_pay_groups` to decide which payroll run to process next based on company status. The framework manages the state of these operations. It ensures that every tool call is tracked and retried if the network hits a snag.

Secure agent tool execution

Require human approval for sensitive actions. Use `get_individual` to pull sensitive data but gate the output behind your agent's safety rules. You keep full control over what the agent can do. The integration ensures that only authorized workflows proceed to the execution phase.

Setup guide

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

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

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

You instantiate the client and spread the tools into your agent definition. This gives your agent immediate access to the full suite of HRIS functions.

Yes. The framework manages retries automatically if a tool call fails. This is critical for payroll jobs that might hit transient network issues.

It is. You can build long-running workflows that call these tools in sequence, ensuring your HR tasks finish without manual intervention.

You can restrict which tools your agent sees by defining a tool filter. This prevents your agent from accessing data it doesn't need for a specific task.

Data is processed in memory during your workflow execution. The server only accesses employment records and salary information when your agent explicitly calls the tools.

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