How to Use the DevSkiller MCP in Mastra AI

Q: How do I require human approval before Mastra AI invites a DevSkiller candidate?

You set requireToolApproval on the invitecandidatetotest tool within your Mastra AI workflow. This pauses the execution and alerts a recruiter to review the candidate profile before sending the test.

Q: Can I query candidate metadata using Mastra AI?

Yes, the agent can call getaccountmetadata to verify your available test limits and active configurations. This helps keep your automated workflows aligned with your current subscription limits.

Automate multi-step DevSkiller hiring workflows with Mastra AI agents and conditional branching.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DevSkiller MCP to Mastra AI

Create your Vinkius account to connect DevSkiller 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 DevSkiller with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Candidate Screening Workflows in Mastra AI

This DevSkiller MCP Server integrates directly with Mastra AI to build automated hiring pipelines. The framework's workflow engine calls `list_assessment_candidates` and routes candidates through custom evaluation logic based on their status. If the candidate has not taken a test, the agent automatically triggers `invite_candidate_to_test` using the workflow's branching logic. This setup handles the entire initial communication loop without requiring manual intervention from your recruiting team.

Resilient Assessment Monitoring and Retries

Mastra AI uses its built-in retry engine to handle temporary DevSkiller API rate limits when fetching results with `get_candidate_assessment_report`. When your agent calls the tool, any network hiccup triggers an exponential backoff instead of failing the workflow. The agent monitors pending invitations by checking `list_test_invitations` on a schedule. If an invitation remains unanswered, the workflow branches to notify a recruiter or send a reminder automatically.

Data-Driven Candidate Routing

Your Mastra AI agent uses the DevSkiller MCP Server to run `list_high_score_candidates` and identify top-tier developers. The workflow automatically extracts the high scorers and forwards their profiles to your team. The agent pulls down the full profile using `get_candidate_profile` to verify background details before routing. This ensures that only fully qualified candidates with verified scores land on your calendar.

Setup guide

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

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

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

You instantiate the MCP client with the server URL and register it in your agent's tool configuration. Mastra AI automatically discovers tools like `list_available_tests` and exposes them to the LLM.

Yes, Mastra AI's workflow engine includes automatic retries with exponential backoff. This prevents your pipeline from breaking if you pull multiple records using `list_assessment_candidates` at once.

You set `requireToolApproval` on the `invite_candidate_to_test` tool within your Mastra AI workflow. This pauses the execution and alerts a recruiter to review the candidate profile before sending the test.

Yes, the agent can call `get_account_metadata` to verify your available test limits and active configurations. This helps keep your automated workflows aligned with your current subscription limits.

The MCP Server processes candidate profiles in ephemeral V8 isolates, meaning no personal information is stored or cached. Your Mastra AI workflows communicate directly with DevSkiller using secure, token-authorized endpoints.

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