How to Use the Height (Project Management) MCP in OpenAI Agents SDK

Q: How do I use the OpenAI Agents SDK to get a summary of a project from Height (Project Management)?

Your agent can use the listtasks tool with a specific list ID to get all relevant tasks. Then, it can iterate through them, calling gettask on each one to build a complete summary of the project's status and blockers.

Q: Can I modify Height tasks with this MCP Server?

No. This server provides read-only tools like gettask and listactivities. This is a deliberate design for safety, ensuring your agents can report on work without any risk of accidentally changing it.

Q: What's the best way to find the right task list with Height (Project Management) and the OpenAI Agents SDK?

Start by having your agent call the listlists tool. This returns all the task lists in your workspace. Your agent can then parse that output to find the ID of the specific list you need for a subsequent listtasks call.

Build production-safe reporting agents for Height with the OpenAI Agents SDK. Get real-time project status without risky write access.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Height (Project Management) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Height (Project Management) 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 Height (Project Management) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Specialized Reporting Agents

This MCP Server gives your agent read-only access to your Height workspace. You can build specialized agents that do one thing well: reporting. Use an agent to poll `list_tasks` for a specific project, then hand off that list to another agent that digs into the details of each ticket with `get_task`. The whole process is governed by the OpenAI Agents SDK's built-in guardrails. Because there are no tools to create or modify tasks, you can deploy these reporting agents with confidence. They can't accidentally change deadlines or delete comments—they just deliver the facts.

Get Full Visibility with Zero Config

Connect the Height MCP Server and your agent instantly discovers all available tools. There's no manual mapping. Your agent can immediately see how to `list_activities` to build a timeline of a project or use `list_users` to check who is assigned to what. This gives your agent the context it needs to answer questions accurately. When someone asks for a status update, the agent has the tools to assemble a real answer based on live data from your workspace, not a guess.

Trace Every Action in Your Dashboard

Every call your agent makes to a Height tool is tracked. When your agent uses `workspace` to get metadata or `list_lists` to find the right task board, you see it in your OpenAI dashboard. This isn't a black box. You get a clear, auditable trail of how your agent gathered its information. It’s perfect for debugging or just confirming that your automations are pulling from the right place. This level of observability is exactly what you need for a production system.

Setup guide

Set up Height (Project Management) 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 Height (Project Management) tools at runtime.
3

Create your Agent

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

Run the agent

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

Your agent can use the `list_tasks` tool with a specific list ID to get all relevant tasks. Then, it can iterate through them, calling `get_task` on each one to build a complete summary of the project's status and blockers.

No. This server provides read-only tools like `get_task` and `list_activities`. This is a deliberate design for safety, ensuring your agents can report on work without any risk of accidentally changing it.

Start by having your agent call the `list_lists` tool. This returns all the task lists in your workspace. Your agent can then parse that output to find the ID of the specific list you need for a subsequent `list_tasks` call.

Vinkius handles the auth for you. You pass a single endpoint token when you instantiate the MCP server in your code. The SDK manages securely passing that token for every subsequent tool call.

The server accesses project and task data from your Height account, including task descriptions, user assignments, and activity logs. Vinkius runs each MCP Server in an ephemeral, zero-trust sandbox. With the OpenAI Agents SDK, every action is traced, giving you a full audit log of what data your agent accessed and when.

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