How to Use the Lunatask MCP in Mastra AI

Q: How do I register the Lunatask tools within a Mastra AI agent?

First, install the @mastra/mcp package and create a new client instance pointing to your server URL. Then, fetch the tools using listTools and spread them directly into your agent's tool configuration array. Mastra handles transport negotiation automatically.

Q: Can Mastra AI read my encrypted Lunatask task names?

No. Because of Lunatask's strict privacy model, the listtasksmetadata tool only returns encrypted metadata like IDs and timestamps. The raw text of your tasks remains encrypted and inaccessible to the model.

Build resilient, automated productivity workflows with Mastra AI and the secure Lunatask MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lunatask MCP to Mastra AI

Create your Vinkius account to connect Lunatask 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 Lunatask with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate habit tracking with Mastra AI

Build agents that monitor your daily routine and log progress automatically. By using the `track_habit_completion` tool, Mastra can trigger habit updates based on external workflow events, like closing a pull request or finishing a calendar event. If the network hiccups or the API rate limits your request, Mastra handles the retry logic automatically. You don't have to write complex failure paths or backoff algorithms. Your habit streaks stay accurate without manual intervention.

Build multi-step task triage pipelines

You can set up workflows that query existing tasks and clean up old backlogs. Use `list_tasks_metadata` to retrieve structural IDs, then feed them to `get_task_metadata` to evaluate priorities. If a task is stale, the agent can call `delete_task` or `update_existing_task` to keep your list clean. Mastra allows you to insert human-in-the-loop approvals before running destructive actions. The MCP client can pause workflows to wait for your final nod before executing the API call. This gives you automated organization without the risk of losing important work.

Secure journal entry automation

Create daily summaries or log development milestones directly into your secure workspace. The `create_journal_entry` tool lets your agent write structured logs directly to your journal based on your daily git commits or calendar events. This automation runs entirely within your self-hosted Mastra environment. Since the API operates on encrypted metadata, your private logs are kept secure from external eyes. You get the benefit of automated journaling without sacrificing your personal privacy.

Setup guide

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

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

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

First, install the `@mastra/mcp` package and create a new client instance pointing to your server URL. Then, fetch the tools using `listTools` and spread them directly into your agent's tool configuration array. Mastra handles transport negotiation automatically.

No. Because of Lunatask's strict privacy model, the `list_tasks_metadata` tool only returns encrypted metadata like IDs and timestamps. The raw text of your tasks remains encrypted and inaccessible to the model.

You can enable Mastra's built-in human-in-the-loop approval feature for the `delete_task` tool. This forces the agent to pause and request your permission before it can remove any task from your account.

Mastra features built-in workflow engines that support automatic retries with exponential backoff. If a tool like `update_existing_task` fails due to a temporary network issue, the engine retries the operation until it succeeds.

This integration relies on a zero-trust model where all transport traffic is encrypted. The server handles only metadata, and your journal text created via `create_journal_entry` is immediately encrypted using local keys before it reaches the cloud storage.

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