How to Use the ONES MCP in Mastra AI

Q: How do I register ONES tools in Mastra AI?

Install @mastra/mcp@latest. Initialize an MCPClient with your endpoint URL, call mcpClient.listTools(), and spread them into your agent's tool array.

Q: Can Mastra AI retry failed ONES task updates?

Yes. If the API rate limits an updatetask call, the framework's built-in retry logic catches the failure and tries again with exponential backoff.

Q: How do I enforce human approval for ONES operations?

Use Mastra's requireToolApproval flag on destructive tools like updatetask or createtask. The agent pauses execution until a human signs off.

Q: Does Mastra AI support conditional branching for ONES tickets?

Yes. You can build logic that checks gettaskdetails. If the ticket is blocked, the workflow branches to alert a manager; if clear, it continues processing.

Build resilient, multi-step ONES workflows that handle task creation, state transitions, and automatic retries using Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ONES MCP to Mastra AI

Create your Vinkius account to connect ONES to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ONES with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Map projects automatically

The ONES MCP Server exposes your entire R&D structure to your Mastra AI agents. Your workflow engine starts by calling `list_projects` to locate the target environment. From there, the agent runs `list_workflows` to map out the exact state transitions allowed. If a transition fails, Mastra catches the error and applies exponential backoff before retrying the call.

Generate tasks with safe fallbacks

Creating tickets in complex enterprise setups often fails due to missing fields. Mastra handles this by chaining `list_task_types` and `list_members` before ever attempting to write data. It verifies the assignee exists and the task type is valid. If `create_task` throws a validation error, the workflow branches conditionally to notify an admin instead of crashing the process.

Update states with human approval

Updating R&D tickets requires precision with this MCP Server. Your agent first uses `get_task_details` to check the current status, ensuring it doesn't overwrite recent human edits. It then fires `update_task` to move the ticket forward. You can wrap this specific tool in Mastra's `requireToolApproval` setting, forcing a human-in-the-loop check before any production state changes.

Setup guide

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

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

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

Install `@mastra/mcp@latest`. Initialize an `MCPClient` with your endpoint URL, call `mcpClient.listTools()`, and spread them into your agent's tool array.

Yes. If the API rate limits an `update_task` call, the framework's built-in retry logic catches the failure and tries again with exponential backoff.

Use Mastra's `requireToolApproval` flag on destructive tools like `update_task` or `create_task`. The agent pauses execution until a human signs off.

Yes. You can build logic that checks `get_task_details`. If the ticket is blocked, the workflow branches to alert a manager; if clear, it continues processing.

This MCP Server reads your internal R&D task descriptions, employee directories, and project states. Mastra runs these operations in your own deployed cloud environment, keeping the tokens and payloads out of third-party hands.

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