How to Use the Monday.com MCP in OpenAI Agents SDK

Q: How do agent handoffs work in Monday.com with the OpenAI Agents SDK?

A dispatcher agent uses listboards to find the target board, then hands off the context to a writer agent. That writer agent uses updateitemcolumns to execute the changes, keeping your production workflows structured and isolated.

Build production agents with the OpenAI Agents SDK that directly modify Monday.com boards while enforcing runtime safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Monday.com MCP to OpenAI Agents SDK

Create your Vinkius account to connect Monday.com 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 Monday.com with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Securely update board values with OpenAI Agents SDK

The `update_item_columns` tool modifies row values on your project boards based on agent decisions. Your Python script initializes the agent with the Monday.com MCP server, allowing OpenAI to route structural updates directly to specific columns. You track these operations via the OpenAI developer dashboard, which traces every tool call to ensure columns map correctly. Built-in guardrails validate each update before execution, preventing your model from injecting malformed JSON into your board schema.

Direct agent handoffs for complex workspace updates

The `list_workspaces` tool reads your active project containers to route tasks to the correct team boards. This MCP integration allows a coordinator agent to scan your account and hand off the execution to a specialized update agent. The secondary agent uses `create_new_item` to build rows with JSON-formatted column data. By using the `async with` context manager in your python code, these agents pass context back and forth without losing the state of the board hierarchy.

Track thread updates using this MCP Server

The `list_item_updates` tool pulls recent row comments to feed conversational history back into your agent. When your system detects a blocker in the comments, it triggers `post_item_update` to post clarifying questions directly to the board. Setting `cacheToolsList=True` during initialization keeps latency low when agents poll these updates. Your OpenAI Agents SDK setup reads these comments as raw strings, enabling your model to formulate responses based on actual team conversations.

Setup guide

Set up Monday.com 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 Monday.com tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Monday.com 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="Monday.com Agent",
            instructions="You have access to Monday.com 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 Monday.com. 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 Monday.com 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 Monday.com MCP in OpenAI Agents SDK

You install the package and pass the Monday.com MCP server endpoint directly to your agent constructor. The agent automatically discovers tools like `list_boards` at runtime, allowing your python code to query and modify boards without manual function mapping.

You control access by managing the exposed endpoint permissions in your Vinkius dashboard. This setup ensures your OpenAI Agents SDK configuration only invokes safe tools like `list_board_items` rather than destructive ones like `remove_item` if you want to restrict agent capabilities.

A dispatcher agent uses `list_boards` to find the target board, then hands off the context to a writer agent. That writer agent uses `update_item_columns` to execute the changes, keeping your production workflows structured and isolated.

The Monday.com API expects structured data for column values, which the `create_new_item` tool enforces. Your agent must format these values as valid JSON strings to prevent the API from rejecting the payload.

Your board columns, item updates, and user profiles never touch persistent external storage. The connection runs through an ephemeral V8 sandbox that processes requests in memory and discards them immediately after execution.

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