How to Use the Beeline MCP in Mastra AI

Build resilient workforce workflows that query Beeline VMS data and handle failures automatically 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 Beeline MCP to Mastra AI

Create your Vinkius account to connect Beeline 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 Beeline with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate job requisition pipelines.

The `list_requisitions` and `search_requisitions` tools pull open contractor roles from Beeline directly into your Mastra AI workflow engine. You set up a scheduled agent to scan for aging job posts. If the query fails due to a network glitch, Mastra triggers an automatic retry with exponential backoff. Finding the right external talent requires constant monitoring. You spread the MCP Server tools into your agent's configuration. The workflow pulls a specific role using `get_requisition`, evaluates the required skills, and conditionally branches to notify different recruiting vendors based on the job category.

Audit timesheets with conditional logic.

Invoking `list_timesheets` alongside `list_expenses` lets your agent cross-reference contractor hours with submitted costs. You build a Mastra workflow that runs every Friday afternoon. The agent checks for discrepancies and uses conditional branching to flag irregular entries for human review. Manual expense auditing wastes hours of HR time. Connecting this MCP integration lets your TypeScript agent handle the initial pass. You can even enforce `requireToolApproval` so a human manager must click approve before the agent proceeds to the next step of the reconciliation pipeline.

Track active worker assignments via Mastra AI.

Calling `list_assignments` grabs the current roster of external workers so your agent can verify contract end dates. You deploy this workflow to your cloud provider with a single command. The agent checks `get_assignment` for each worker nearing their termination date. Offboarding contractors securely means hitting deadlines. If an assignment ends next week, the Mastra workflow branches to alert IT. It automatically detects the streamable HTTP transport from Vinkius, ensuring stable connections while processing hundreds of external worker records.

Setup guide

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

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

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

Install @mastra/mcp and instantiate MCPClient with your Vinkius URL in the servers object. Call mcpClient.listTools() and spread the results into your agent's tool array. Mastra handles the transport detection automatically.

The framework includes built-in exponential backoff for all tool calls. If the VMS API drops the connection during a timesheet fetch, the agent waits and tries again. You configure the retry limits in your workflow definition.

Set the requireToolApproval flag to true when configuring your agent. The workflow pauses execution when it hits the expense listing tool. A manager reviews the proposed action before the agent continues processing the external workforce data.

You can build multi-step pipelines that pull assignments, check requisitions, and format reports. Conditional branching lets the agent take different paths based on the tool outputs. Deploying these pipelines takes one command.

Worker profiles, supplier rates, and assignment dates pass through a zero-trust architecture. Vinkius executes the Mastra tool calls inside isolated sandboxes that vanish instantly after the data returns. Your endpoint token is the only credential exposed to the network.

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