How to Use the Mela MCP in Mastra AI

Q: How do I initialize the Mela MCP Server inside Mastra AI?

Install @mastra/mcp and instantiate the client with the Mela endpoint URL. Register the tools in your agent config by calling mcpClient.listTools() to let Mastra handle the transport.

Q: Can I require human approval before Mastra AI updates Mela?

Yes, you can use Mastra's requireToolApproval hook. This pauses the workflow when the agent tries to run updateactivitystatus or log costs until a manager manually approves.

Q: Can I build conditional loops based on Mela checklist data?

Absolutely. Your agent can fetch tasks via listchecklists and loop through them, executing logworkhours only when specific checklist items remain incomplete.

Q: Where does my Mela financial data go when using Mastra AI?

Financial data pulled by getaccountingdata travels through Vinkius's zero-trust sandboxes directly to your secure Mastra runtime. Your accounting details remain isolated within the secure MCP runtime.

Build resilient, self-healing Mela workflows with Mastra AI workflows and automatic retry logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mela MCP to Mastra AI

Create your Vinkius account to connect Mela 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 Mela with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient field logging with Mastra AI workflows

`log_work_hours` acts as the entry point for automated labor logging pipelines built with Mastra AI. This MCP Server ensures that if a field worker submits hours on a spotty network, Mastra retries the request until it registers. The workflow then transitions to `log_materials` to track resource consumption under the same job code. By chaining these tools, your Mastra agent keeps labor and material records perfectly synced.

Automated budget alerts and status updates

`get_accounting_data` retrieves cost metrics that trigger conditional branching in your Mastra agent. If an activity exceeds its budget, the workflow routes the alert to managers instead of continuing blindly. The agent then calls `post_message` to post an urgent warning directly to the Mela activity feed. If the overage is severe, the workflow executes `update_activity_status` to pause the project automatically.

Multi-step site onboarding using Mastra AI

`create_activity` initializes a new job site inside the Mela workspace with a single Mastra agent command. The workflow automatically populates the site with necessary checklists and team assignments. Next, the agent calls `list_teams` and `list_users` to assign supervisors to the new site. This eliminates the manual setup overhead when spinning up dozens of new projects simultaneously.

Setup guide

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

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

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

Install `@mastra/mcp` and instantiate the client with the Mela endpoint URL. Register the tools in your agent config by calling `mcpClient.listTools()` to let Mastra handle the transport.

Yes, you can use Mastra's `requireToolApproval` hook. This pauses the workflow when the agent tries to run `update_activity_status` or log costs until a manager manually approves.

Mastra uses an exponential backoff engine to retry failed calls to our MCP tools like `post_message` or `log_materials`. If a temporary network glitch occurs, the framework retries the call automatically.

Absolutely. Your agent can fetch tasks via `list_checklists` and loop through them, executing `log_work_hours` only when specific checklist items remain incomplete.

Financial data pulled by `get_accounting_data` travels through Vinkius's zero-trust sandboxes directly to your secure Mastra runtime. Your accounting details remain isolated within the secure MCP runtime.

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