How to Use the TrackingTime MCP in AutoGen

Q: Can AutoGen manage my team members?

Yes. You can pass the list of users obtained from listworkspaceusers into a debate cycle. The agents discuss resource availability and then generate a final roster that you can use.

Q: What's the process for updating tasks with AutoGen?

The system uses multiple perspectives to decide how to update a task, calling updatetask only after all agents agree on the necessary changes and their impact.

Q: What specific data does this MCP Server touch regarding privacy?

This server touches user identification records (getuserprofile), project lists (listprojects), and time logs (listtimeentries).

Achieve consensus on tasks with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect TrackingTime MCP to AutoGen

Create your Vinkius account to connect TrackingTime 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 TrackingTime with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate task creation using MCP Server

When your multi-agent system needs to add a task, it can use `create_task`. The agents debate the scope and owner of the task until they reach consensus. This result is then passed to the tool for execution. The process ensures that every required field is filled out because multiple agents challenge each other's inputs before committing the change via the MCP Server.

Review project status with AutoGen

The agents can gather all necessary information by first calling `list_projects` and then iterating through that list. They debate which projects are stalled versus those on track. The final decision—the 'consensus' report—is a structured summary of the project statuses, synthesized from multiple data points pulled via the tools.

Debate time logging with AutoGen

If your agents need to log time, one agent might call `start_timer`, while another challenges it by asking for prior context using `list_time_entries`. They discuss if the current task matches past efforts. The outcome is a validated time log entry. The system doesn't just record; it validates the recording through simulated debate.

Setup guide

Set up TrackingTime 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 TrackingTime 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="TrackingTime_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent TrackingTime 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="TrackingTime_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent TrackingTime 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 TrackingTime. 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 TrackingTime 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 TrackingTime MCP in AutoGen

The multi-agent framework allows different agents to review your time logs. For instance, one agent checks for consistency using `list_time_entries`, while another ensures the task was properly updated via `update_task`.

Yes. You can pass the list of users obtained from `list_workspace_users` into a debate cycle. The agents discuss resource availability and then generate a final roster that you can use.

The system uses multiple perspectives to decide *how* to update a task, calling `update_task` only after all agents agree on the necessary changes and their impact.

Yes. You can build pipelines where one agent reads client data (`list_customers`), another calculates required work time, and a third finally executes `add_time_entry` based on the consensus.

This server touches user identification records (`get_user_profile`), project lists (`list_projects`), and time logs (`list_time_entries`).

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