How to Use the Troops MCP in Mastra AI

Q: How can I handle candidate data with Troops and Mastra AI?

You use getcandidate to pull data. If that retrieval fails due to a temporary network issue, Mastra AI's built-in retry logic handles it automatically. The workflow keeps running until the data is successfully retrieved.

Q: What happens if I try to list jobs with Troops and Mastra AI?

If listjobs encounters a temporary API error, your complex workflow doesn't stop. Mastra AI will automatically retry the listing operation using its failure handling mechanisms until it gets valid results.

Q: If I need to create a contract with Troops and Mastra AI, what steps does the system take?

You call generatecontract. If the generation fails (maybe due to missing client IDs), the workflow can branch: it notifies an admin for manual input or tries a different format.

Q: How do I submit timesheets with Troops and Mastra AI?

You use submittimesheet. This is ideal because if the submission fails, the workflow can be configured to wait an hour and retry the operation automatically. It's built for resilience.

Build complex, failure-proof HR workflows and logic using Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Troops MCP to Mastra AI

Create your Vinkius account to connect Troops 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 Troops with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Candidate Workflows

The `create_candidate` tool registers a new applicant into your system. Because you're on Mastra AI, if the initial API call fails, the workflow automatically retries with exponential backoff until it succeeds. You can check existing details using `get_candidate`. If that lookup times out, the whole process doesn't crash; Mastra handles the failure gracefully and notifies an admin.

Orchestrate Job Offers

To publish a new opening, you use the `create_job` tool. This is critical because complex workflows need reliability—if publishing fails, your multi-step process knows exactly how to recover. You can also list offers using `list_jobs`. Mastra AI's built-in engine allows you to build conditional logic around this; for example, if the status is 'archived,' it triggers a different notification path.

Process Contracts and Paychecks

The `generate_contract` tool creates legal documents. If the required inputs are missing, Mastra's workflow engine catches the failure and forces the user to approve the necessary data before retrying. For timekeeping, you use `submit_timesheet`. This is a perfect multi-step process: submit timesheet -> check status -> if successful, trigger contract generation.

Setup guide

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

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

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

You use `get_candidate` to pull data. If that retrieval fails due to a temporary network issue, Mastra AI's built-in retry logic handles it automatically. The workflow keeps running until the data is successfully retrieved.

If `list_jobs` encounters a temporary API error, your complex workflow doesn't stop. Mastra AI will automatically retry the listing operation using its failure handling mechanisms until it gets valid results.

This server touches sensitive HR data, including candidate details, job offers, signed contracts, and timesheet submissions. Mastra AI ensures these operations are handled reliably through its workflow engine.

You call `generate_contract`. If the generation fails (maybe due to missing client IDs), the workflow can branch: it notifies an admin for manual input or tries a different format.

You use `submit_timesheet`. This is ideal because if the submission fails, the workflow can be configured to wait an hour and retry the operation automatically. It's built for resilience.

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