How to Use the HRBlade MCP in Mastra AI

Q: How do I set up the HRBlade MCP server in Mastra AI?

Install the @mastra/mcp package and create a new MCPClient. Pass your HRBlade server URL from Vinkius into the configuration. Your agents can then access the tools to build workflows.

Q: Is it possible to require human approval before sending an interview?

Yes. Mastra has a requireToolApproval option. Your workflow can prepare an invite, then pause for a human-in-the-loop to approve it before the sendinterviewinvitation tool is actually executed.

Build bulletproof hiring workflows with HRBlade and Mastra AI. Automate invites, track responses, and handle errors without writing tons of code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HRBlade MCP to Mastra AI

Create your Vinkius account to connect HRBlade 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 HRBlade with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Your Entire Hiring Funnel

This MCP server lets you build a hands-off recruiting workflow. Set up a Mastra agent that periodically calls `list_candidates` to find new applicants. For each new person, it can automatically call `send_interview_invitation`. Here’s the thing: you don't have to worry about transient API errors. If a call to `send_interview_invitation` fails, Mastra’s built-in exponential backoff and retry logic will handle it. No dropped invitations.

Create Smart Hiring Logic with Mastra AI

The HRBlade tools are simple, but you can build complex systems with them in Mastra. For example, a workflow can use `get_candidate_details` to check a custom field. If a candidate is tagged as 'priority', the agent immediately sends an invite for a specific role. If not, the agent can add them to a different workflow for a standard screening. This lets you build rule-based automation that adapts to your team's needs, and it runs reliably in the background.

Reliably Track Interview Status

You can create a scheduled Mastra workflow that acts as a monitor. Every hour, it calls `list_interview_responses` to check for new video submissions from candidates. When it finds a new response, it can trigger any other action you need—notifying a hiring manager in Slack, updating a database, or moving the candidate to the next stage in another system. The workflow engine guarantees every response gets processed.

Setup guide

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

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

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

Install the `@mastra/mcp` package and create a `new MCPClient`. Pass your HRBlade server URL from Vinkius into the configuration. Your agents can then access the tools to build workflows.

Yes, that's what Mastra is designed for. You can chain tools like `send_interview_invitation`, add a delay, then call `list_interview_responses` to check for a submission, all inside a single, durable workflow.

Mastra has automatic retries with configurable backoff. If an API call to HRBlade fails because of a temporary network issue, Mastra retries it for you. This makes your automation much more resilient.

Yes. Mastra has a `requireToolApproval` option. Your workflow can prepare an invite, then pause for a human-in-the-loop to approve it before the `send_interview_invitation` tool is actually executed.

Your HRBlade server only processes candidate information and interview response metadata. It operates within a zero-trust, ephemeral Vinkius sandbox. Your Mastra agent communicates with it over a TLS-encrypted connection, and no PII is persisted on the MCP server.

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