How to Use the Lucca (HR & Finance Suite) MCP in Mastra AI

Q: How do I register the Lucca (HR & Finance Suite) tools inside a Mastra AI agent?

Install @mastra/mcp@latest and initialize new MCPClient with your Vinkius endpoint URL. Call mcpClient.listTools() and spread the resulting tools directly into your Agent's tool array.

Q: Can Mastra AI handle multi-step approval flows for Lucca (HR & Finance Suite) leave requests?

Yes, you can build a workflow that runs listleaves to find pending requests, checks balances with getleavebalances, and uses requireToolApproval to ask an HR manager for sign-off before proceeding.

Build resilient HR workflows with Mastra AI and the Lucca MCP Server to automate expense approvals and leave tracking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lucca (HR & Finance Suite) MCP to Mastra AI

Create your Vinkius account to connect Lucca (HR & Finance Suite) 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 Lucca (HR & Finance Suite) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Expense Verification Workflows

The `list_expense_reports` tool lets your Mastra AI agents pull Cleemy records and feed them into conditional execution pipelines. If an expense report exceeds a set threshold, the workflow automatically triggers a retry or routes it to a manager. You use `list_expense_claims` to check individual receipts before marking a report as ready for payroll. Mastra's built-in workflow engine handles API rate limits and temporary network drops with exponential backoff. You register the server using `new MCPClient` and spread the tools into your agent configuration. The framework's state machine ensures that financial data moves safely between Lucca and your accounting systems.

Self-Healing Leave and Timesheet Syncing

The `list_timesheets` tool retrieves Timmi timesheet records to reconcile them against planned absences. Mastra AI agents monitor these records, automatically flagging discrepancies where hours don't match. If a lookup fails, the framework retries the call to `list_leaves` to ensure no vacation days are missed. You can set up human-in-the-loop validation using Mastra's `requireToolApproval` feature. Before writing any corrections back to your database, the agent pauses and waits for an HR manager to sign off. This keeps your records accurate without giving the model unchecked write access.

Dynamic Directory Mapping with Mastra AI

The `list_users` tool allows your Mastra AI agents to build up-to-date organizational maps. When a new department is created, the agent calls `list_departments` to categorize users correctly. It can then fetch individual profiles using `get_user` to update internal directory databases. This setup runs on any cloud with a simple one-command deploy. The framework auto-detects the Vinkius transport protocol, whether you use standard SSE or Streamable HTTP. Your agents can run autonomously in the background, keeping your HR systems in sync with external directories.

Setup guide

Set up Lucca (HR & Finance Suite) 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 Lucca (HR & Finance Suite) 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: "lucca-hr-finance-suite-mcp-client",
  servers: {
    "lucca-hr-finance-suite-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Lucca (HR & Finance Suite) 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 Lucca. 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 Lucca (HR & Finance Suite) 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 Lucca (HR & Finance Suite) MCP in Mastra AI

Install `@mastra/mcp@latest` and initialize `new MCPClient` with your Vinkius endpoint URL. Call `mcpClient.listTools()` and spread the resulting tools directly into your Agent's tool array.

Yes, you can build a workflow that runs `list_leaves` to find pending requests, checks balances with `get_leave_balances`, and uses `requireToolApproval` to ask an HR manager for sign-off before proceeding.

Mastra AI's workflow engine automatically manages transient errors and rate limits. If a call to `list_expense_reports` gets blocked, the engine uses exponential backoff to retry the request without breaking the execution state.

Yes. The integration supports both standard SSE and Streamable HTTP, allowing you to use Vinkius's highly optimized endpoints to fetch employee data.

No employee directory data is stored permanently. Vinkius executes all calls to `get_user` and `list_users` in a zero-trust, ephemeral V8 isolate. Your sensitive HRIS directory data is only read in transit to satisfy the agent's immediate workflow step.

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