How to Use the Height (Project Management) MCP in AutoGen

Q: How do I configure AutoGen to use the Height (Project Management) MCP Server?

Use mcpservertools with StreamableHttpServerParams to fetch the endpoints. Pass the returned list directly to your AssistantAgent constructor.

Give AutoGen multi-agent systems read access to your Height project data.

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 AutoGen

Create your Vinkius account to connect Height (Project Management) to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Tasks via MCP Server

The `get_task` and `list_tasks` tools feed live ticket details directly into AutoGen conversations. One agent can pull a list of open bugs while another reviews the descriptions. They debate the priority based on the actual text in the tickets. This setup replaces static reports with active negotiation. A QA agent might argue a bug is critical, while a product agent pushes back based on the task history. They reach a consensus using real data.

Audit Workspace Activity

The `list_activities` tool provides a factual record of what happened in the project. When agents disagree about a timeline, they can query the audit log to settle the dispute. Hard data resolves the conflict immediately. They can also check `workspace` and `list_lists` to understand where a task belongs. If an agent suggests moving a ticket, it verifies the destination list exists first. The conversation stays grounded in reality.

Verify User Assignments

The `list_users` tool lets your agents check who is available before recommending task assignments. A planning agent pulls the roster, while a resource agent checks current workloads. They negotiate the best distribution of labor. You build systems that actually understand your team capacity. The agents stop hallucinating names or assigning work to deleted accounts. They rely on the exact user data returned by the API.

Setup guide

Set up Height (Project Management) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Height (Project Management) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Height (Project Management)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Height (Project Management) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Height (Project Management)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Height (Project Management) data")
    print(result.messages[-1].content)

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 AutoGen

Use mcp_server_tools with StreamableHttpServerParams to fetch the endpoints. Pass the returned list directly to your AssistantAgent constructor.

Yes, you can equip any number of agents with the same toolset. We recommend giving read access to a specific researcher agent that answers questions from the rest of the group.

No. The available endpoints are strictly for reading data. Your agents can debate priorities and analyze workloads, but they cannot create or close tasks in the system.

The McpToolAdapter handles it automatically in the background. You do not need to write custom JSON schemas for endpoints like get_task or list_users.

Task descriptions and activity logs stream through an isolated, ephemeral sandbox. Vinkius requires just one endpoint token to authenticate the session. The connection drops immediately after the agents finish their conversation, leaving no trace.

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