How to Use the KanbanTool MCP in Mastra AI

Q: How do I register the KanbanTool MCP Server inside a Mastra AI agent?

Instantiate the MCPClient with your Vinkius server URL and pass the tools returned by mcpClient.listTools() to your agent. This grants your Mastra agent immediate access to tools like listboards and createtaskcard.

Q: How do I build a branching workflow based on board activity?

You can configure your agent to query listtaskactivities first. Based on the returned history, the agent can branch to either update the card using updatetaskdetails or escalate the issue to a team lead.

Build resilient TypeScript workflows that auto-retry task creation and branch logic using the KanbanTool MCP Server and 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 KanbanTool MCP to Mastra AI

Create your Vinkius account to connect KanbanTool 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 KanbanTool with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build resilient KanbanTool workflows using Mastra AI

The `create_task_card` tool integrates directly into Mastra AI's workflow engine to build automated, self-healing task creation pipelines. If an API call fails due to network issues, Mastra's built-in exponential backoff automatically retries the card creation without crashing your agent. You can write conditional branching logic that checks `get_user_profile` to assign tasks to the correct team member automatically. If a developer is over capacity, the workflow dynamically routes the card to an available peer.

Automate board cleanup with conditional branching

The `archive_task_card` tool allows your Mastra agent to clean up stale items based on strict inactivity metrics. This background engine queries `list_task_activities` to check when a card was last updated before making the decision to archive. Automation like this prevents visual clutter on your boards without requiring manual intervention. You can configure a human-in-the-loop approval step using Mastra's `requireToolApproval` before the agent actually archives any critical work.

Sync external tools using this custom MCP Server

The `update_task_details` tool lets your Mastra agent sync task statuses with external databases or code repositories. When a developer closes a pull request, the workflow triggers and updates the corresponding card automatically. By using `list_shared_links`, your automated workflows can also generate and distribute public board views to clients whenever a major milestone is reached. This keeps your external stakeholders updated without exposing your internal development boards.

Setup guide

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

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

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

Instantiate the `MCPClient` with your Vinkius server URL and pass the tools returned by `mcpClient.listTools()` to your agent. This grants your Mastra agent immediate access to tools like `list_boards` and `create_task_card`.

Yes, Mastra's workflow engine has native support for automatic retries with exponential backoff. If `update_task_details` fails due to a temporary network blip, the engine retries the operation automatically.

Mastra connects to the Vinkius managed endpoint using a single transport token. This token acts as the gatekeeper, letting the agent hit the KanbanTool API securely without exposing raw developer keys in your workflow code.

You can configure your agent to query `list_task_activities` first. Based on the returned history, the agent can branch to either update the card using `update_task_details` or escalate the issue to a team lead.

Vinkius runs this MCP Server in an ephemeral, zero-trust sandbox that processes your task descriptions and user profiles in memory without persistent storage. All credentials are encrypted, ensuring your private board data remains completely secure.

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