How to Use the HiFlow MCP in Mastra AI

Q: How do I configure Mastra AI to use HiFlow tools?

Install @mastra/mcp@latest. Initialize an MCPClient with your server URL, then call mcpClient.listTools() and spread the results into your Agent's tool array. The client automatically detects if you need SSE or Streamable HTTP.

Q: How do I require approval before creating a HiFlow customer in Mastra AI?

You set the requireToolApproval flag on the createcustomer tool in your agent definition. The workflow will halt and wait for a human to review the payload before sending the actual POST request.

Q: Can I branch logic based on an estimate's value?

Definitely. Your agent fetches the quote using getestimate. You then write a conditional branch in your workflow that routes high-value quotes to a manager's queue while auto-approving smaller ones.

Build resilient billing and job workflows by connecting HiFlow to 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 HiFlow MCP to Mastra AI

Create your Vinkius account to connect HiFlow 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 HiFlow with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient MCP Server Billing Workflows

The `list_invoices` and `get_invoice` tools allow your agents to audit billing records automatically. Mastra AI wraps these calls in its workflow engine, meaning if an API timeout occurs, the system automatically triggers an exponential backoff retry. You can build a condition where the agent checks an invoice status, and if it remains unpaid, it branches off to pull the client details using `get_customer`. The script handles the failure gracefully without manual intervention.

Automated Timesheet Audits

The `list_timesheets` tool feeds raw hour logs directly into your agent's context window. You set up a scheduled workflow that pulls these records every Friday afternoon to check for missing entries. If the agent spots a gap, it can query `get_job` to see what the team was actually working on. You deploy this logic to your cloud provider with a single command, turning a manual HR task into a background process.

Human-in-the-Loop Job Creation

The `create_customer` tool writes new records to your database. Because writing data carries risk, you can enable the `requireToolApproval` setting in your Mastra configuration. The agent prepares the customer profile based on incoming emails, pauses execution, and pings an admin for approval. Once cleared, it executes the tool and follows up by pulling the new profile with `get_customer` to verify the write.

Setup guide

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

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

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

Install `@mastra/mcp@latest`. Initialize an `MCPClient` with your server URL, then call `mcpClient.listTools()` and spread the results into your Agent's tool array. The client automatically detects if you need SSE or Streamable HTTP.

Yes. The framework's built-in workflow engine handles transient errors natively. If a call to `get_job` drops, the agent applies exponential backoff and tries again before marking the step as failed.

You set the `requireToolApproval` flag on the `create_customer` tool in your agent definition. The workflow will halt and wait for a human to review the payload before sending the actual POST request.

Definitely. Your agent fetches the quote using `get_estimate`. You then write a conditional branch in your workflow that routes high-value quotes to a manager's queue while auto-approving smaller ones.

Vinkius routes every request through a zero-trust architecture. When your agent calls `list_timesheets`, it authenticates via a single endpoint token, executes the read operation in an isolated container, and terminates the connection. No persistent tunnels exist.

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