How to Use the DeskTime MCP in Mastra AI

Q: How do I use DeskTime tools in a Mastra AI agent?

After npm install @mastra/mcp, you create a new MCPClient and point it to your Vinkius server URL. Then you can call mcpClient.listTools() and spread the result into your agent's tool configuration.

Q: Can I require human approval before my Mastra agent deletes a DeskTime project?

You can. Mastra AI supports a requireToolApproval option. When you configure the removeproject tool, you can set it to pause the workflow and wait for a person to approve the action before it runs.

Automate complex DeskTime workflows with Mastra AI. Build reliable, multi-step agents that manage projects, track performance, and handle errors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeskTime MCP to Mastra AI

Create your Vinkius account to connect DeskTime 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 DeskTime with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Resilient Project Automation

Use Mastra AI to create workflows that manage your DeskTime projects. Your agent can use `create_project` and then follow up with a series of `create_new_task` calls to populate it. The real power is in the error handling. If a network hiccup causes a tool to fail, Mastra's built-in exponential backoff handles the retry automatically. You can also define conditional logic: if `create_project` fails for a specific reason, your workflow can branch to notify an admin instead of just stopping.

Create Reliable Reporting Pipelines

This MCP server gives your agent tools to check on team performance. A Mastra agent can run on a schedule to fetch daily numbers using `get_productivity_reports` and `get_employee_performance`. This isn't just a simple cron job. Mastra's workflow engine ensures the job gets done. If the DeskTime API is temporarily unavailable, your agent will wait and retry, ensuring you get your reports without manual intervention.

Set Up Conditional Staff Monitoring

You can build an intelligent agent that checks on your team and acts on what it finds. For example, a workflow could use `list_online_staff` to check who is active. If a key team member isn't online by a certain time, the agent could trigger another action. It can also get more specific. The agent could check project status with `get_project_details` and, if it's behind schedule, automatically use `create_new_task` to add a 'Follow-up' item for the project manager.

Setup guide

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

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

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

After `npm install @mastra/mcp`, you create a `new MCPClient` and point it to your Vinkius server URL. Then you can call `mcpClient.listTools()` and spread the result into your agent's tool configuration.

Yes, that's a core feature of Mastra AI. It has automatic retries with exponential backoff built in. Your agent will re-run a failed call to `get_productivity_reports` without you writing any extra code.

Mastra's workflow engine is designed for this. You can define a conditional path that executes only if the `create_project` tool fails. That path could log the error, send a Slack message, or try creating the project with different parameters.

You can. Mastra AI supports a `requireToolApproval` option. When you configure the `remove_project` tool, you can set it to pause the workflow and wait for a person to approve the action before it runs.

The server processes your company's project, task, and employee data from DeskTime. Every request is handled in a separate, ephemeral sandbox that's torn down right after. All traffic is encrypted and secured by your personal auth token.

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