How to Use the Checkr MCP in Mastra AI

Q: How do I connect the Checkr MCP to my Mastra AI agent?

In your Mastra MCPClient setup, you just add the Checkr server name and the unique URL Vinkius provides. Mastra will automatically detect the available tools like createnewcandidate and make them available to your agent.

Build resilient, automated hiring workflows on Checkr with 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 Checkr MCP to Mastra AI

Create your Vinkius account to connect Checkr 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 Checkr with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fully Automated Candidate Screening

This is for hands-off automation. A Mastra workflow can trigger on a new applicant, call `create_new_candidate`, and then immediately `start_background_check`. No human needs to be involved. Mastra's engine handles the sequence and any required retries. You can build in conditional logic that simple scripts can't handle. For instance, use `list_screening_invitations` to check if an invite was completed. If not, your workflow can wait 24 hours and trigger a reminder. That's real automation.

Branch Workflows on Report Status

Don't just run checks, act on them. Your Mastra agent can run `get_report_details` and parse the status. If it's 'clear', the workflow continues to the next step. If it's 'consider', the workflow can branch—pausing the process and notifying a human for review. This turns your agent from a simple tool-caller into a process owner. Mastra's built-in retry logic means that if a call to the Checkr MCP Server fails because of a network blip, it will just try again automatically. Your workflow won't crash.

Scheduled Audits and Reporting

Set up a scheduled job in Mastra to run a weekly audit. The agent can use `list_checkr_candidates` and `list_background_reports` to get a complete snapshot of your account's activity. Your workflow can then process this data. You can have it count pending reports, calculate average turnaround time, or flag reports that have been stuck in 'consider' status for too long. It's how you build operational intelligence around your hiring process.

Setup guide

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

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

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

Use the output of one tool as the input for your logic. For example, call `get_report_details`, then use a simple 'if' statement in your workflow to check if the report status is 'clear' or 'consider' before deciding which tool to call next.

Yes, that's a core feature of the Mastra framework. It has built-in support for retries with exponential backoff. If the MCP Server is temporarily unavailable, your workflow will wait and try again instead of failing.

In your Mastra `MCPClient` setup, you just add the Checkr server name and the unique URL Vinkius provides. Mastra will automatically detect the available tools like `create_new_candidate` and make them available to your agent.

Yes. Mastra supports human-in-the-loop actions. You can configure your agent with `requireToolApproval` for sensitive tools like `start_background_check`, which will pause the workflow until a person gives the go-ahead.

Your Checkr data is processed inside a Vinkius zero-trust sandbox. The server is ephemeral, meaning it's created for your workflow and destroyed immediately after. For extra control, use Mastra's `requireToolApproval` setting to require a human to sign off before the agent accesses sensitive candidate information.

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