How to Use the KanbanTool MCP in OpenAI Agents SDK

Connect the KanbanTool MCP Server to the OpenAI Agents SDK to build production-ready agents that manage boards under strict guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect KanbanTool to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate board operations with OpenAI Agents SDK

Your production agent needs to read real KanbanTool boards instead of guessing status updates. By connecting this MCP Server, your OpenAI agent reads your active workspace using `list_boards` and pulls the exact columns via `get_board_details`. It knows exactly where bottlenecks live before making a single change. Guardrails matter when an autonomous system touches your task tracker. You configure handoffs so a specialized triage agent runs `create_task_card` for incoming bug reports, while a separate project manager agent uses `update_task_details` to move them across the board. Every action shows up in your OpenAI tracing dashboard.

Audit workflows through task history

Blind spots kill autonomous systems. When your agent needs to figure out why a feature is delayed, it runs `list_task_activities` to pull the complete event history. It reads the actual comments and status shifts instead of assuming what happened. You get full visibility into the agent's logic. If it decides a stalled item needs to be removed, it executes `archive_task_card`. You validate that decision in the OpenAI logs, ensuring the agent follows your defined safety constraints before hiding work.

Connect external clients to agent progress

Stakeholders want to see what your multi-agent system is doing without logging into the platform. Your agent pulls public views using `list_shared_links` and emails them to external partners. They see the real-time board state exactly as the system updates it. This keeps your core engineering data isolated. The agent handles the deep inspection via `get_task_details` and `list_board_tasks` internally, but only exposes the read-only shared links to outsiders. It's a clean boundary for production deployments.

Setup guide

Set up KanbanTool MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all KanbanTool tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives KanbanTool tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate KanbanTool tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="KanbanTool Agent",
            instructions="You have access to KanbanTool tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Run pip install openai-agents. You initialize the connection using MCPServerStreamableHttp with your endpoint URL. Pass it into the mcp_servers array in your Agent constructor, and it auto-discovers the toolset.

Yes. You apply built-in guardrails to limit the agent to read-only tools like get_board_details and list_board_tasks. If you want to allow writes, explicitly approve update_task_details in your safety constraints.

You likely forgot to enable the cache. Set cacheToolsList=True in your server parameters. The SDK needs this to register tools efficiently during the async context manager setup.

Absolutely. A support agent receives an issue, then hands off the context to a developer agent that runs get_task_details to investigate the newly created card.

The MCP server reads exact task descriptions and user assignments via get_task_details and get_user_profile. Vinkius runs this connection in an ephemeral, zero-trust V8 Isolate Sandbox. The agent only accesses the specific board data you authorize, and the sandbox dies the moment the session ends.

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