How to Use the Manatal MCP in Mastra AI

Q: Can I build conditional branching based on Manatal job departments in Mastra AI?

Yes. You can route candidates by calling listdepartments and checking their applied job with getjob, then branch your Mastra AI workflow depending on the department ID.

Q: How do I register the Manatal MCP Server tools in Mastra AI?

Instantiate the MCPClient with your Vinkius URL, call listTools(), and spread them directly into your Mastra AI agent's tool block to expose endpoints like listcandidates.

Q: Does Mastra support human-in-the-loop approvals for ATS actions?

Yes. You can set requireToolApproval on critical tools like getapplication to ensure a human reviews the Manatal data before the Mastra AI agent proceeds with the workflow.

Q: How does Mastra AI protect sensitive Manatal candidate profiles?

All data payloads from getcandidate and listcandidates pass directly through Vinkius's zero-trust MCP sandbox. No candidate emails, phone numbers, or resume texts are stored on the host platform.

Run autonomous ATS workflows that sync Manatal candidates and handle API retries 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 Manatal MCP to Mastra AI

Create your Vinkius account to connect Manatal 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 Manatal with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build automated screening pipelines in Mastra AI

The `list_candidates` tool fetches new applicants so your Mastra AI workflow can run them through custom evaluation steps. If a candidate matches your criteria, the Mastra AI workflow triggers conditional branching to schedule interviews or update status fields in Manatal. By calling `get_candidate`, the Mastra AI agent digs into specific resume details and skills to verify experience levels. Mastra AI handles the Manatal API retries automatically if the server hits rate limits, so your hiring pipeline doesn't stall during peak application periods.

Sync jobs and departments via MCP Server

The `list_jobs` tool pulls active job postings to keep your external databases and Mastra AI workflows perfectly aligned. This MCP Server lets your Mastra AI agents monitor open Manatal roles and flag any discrepancies across your HR ecosystem. Workflows use `list_departments` and `get_job` to map Manatal roles to the correct business units inside Mastra AI without manual data entry. If a department head modifies a role, the Mastra AI agent detects the shift in Manatal and updates your internal org charts instantly.

Route applications dynamically based on status

The `list_applications` tool tracks candidate progress across all active Manatal hiring pipelines. Mastra AI agents monitor this tool to trigger alerts when an applicant stays in one stage for too long. When a bottleneck occurs, the Mastra AI workflow calls `get_application` to extract recruiter feedback and route it to the hiring manager. This automated escalation keeps your Manatal hiring cycle moving so you don't have to manually check each status.

Setup guide

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

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

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

Mastra AI features a built-in workflow engine with automatic retries. If `get_candidate` or `list_applications` fails due to temporary network issues, the Mastra AI system backs off and retries without dropping the execution.

Yes. You can route candidates by calling `list_departments` and checking their applied job with `get_job`, then branch your Mastra AI workflow depending on the department ID.

Instantiate the `MCPClient` with your Vinkius URL, call `listTools()`, and spread them directly into your Mastra AI agent's tool block to expose endpoints like `list_candidates`.

Yes. You can set `requireToolApproval` on critical tools like `get_application` to ensure a human reviews the Manatal data before the Mastra AI agent proceeds with the workflow.

All data payloads from `get_candidate` and `list_candidates` pass directly through Vinkius's zero-trust MCP sandbox. No candidate emails, phone numbers, or resume texts are stored on the host platform.

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