How to Use the Everhour Time Tracking MCP in AutoGen

Q: How do I register the Everhour Time Tracking MCP Server in AutoGen?

Run pip install -U autogen-extmcp. Use mcpservertools with StreamableHttpServerParams to fetch the tools, then pass that list directly to your AssistantAgent constructor.

Q: Can agents debate the output of Everhour Time Tracking time records?

Yes. One agent can interpret the raw hours from listteamtimerecords, while another cross-references those hours against the budget data from getprojectdetaileddata to argue about project profitability.

Q: Does the AutoGen adapter handle the API schema automatically?

Yes. The McpToolAdapter automatically converts the JSON schema for tools like quicktimetrackingaudit into a format your agents understand, so you do not have to write custom parsers.

Give your AutoGen multi-agent systems the ability to debate project budgets and audit time records.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Everhour Time Tracking MCP to AutoGen

Create your Vinkius account to connect Everhour Time Tracking 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 Everhour Time Tracking with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent project auditing

You build a system where an accounting agent and a project management agent debate resource allocation. The accounting agent runs `get_project_detailed_data` to check the budget, while the PM agent pulls `list_project_tasks` to see the remaining work. They negotiate the reality of the project. If the accounting agent flags a budget overrun using `list_projects_within_budget`, the PM agent counters by analyzing the recent entries from `quick_time_tracking_audit`. They reach a consensus before alerting a human.

Connect the MCP Server to AutoGen

The Everhour Time Tracking integration feeds raw API data directly into your conversation loops. One agent triggers `list_organization_team_members` to establish the roster, passing the IDs to a secondary agent for time verification. The secondary agent executes `list_team_time_records` and formats the findings. If it spots a discrepancy, it challenges the primary agent's assumptions. You watch the system deliberate over the data instead of blindly executing a script.

Active timer monitoring and alerts

A dedicated monitoring agent polls `get_currently_running_timer` to watch for unusual activity. If it detects a timer running for 12 hours, it messages a supervisor agent to decide what to do. The supervisor agent pulls the user's profile via `get_everhour_user_metadata` and checks the client context using `list_billing_clients`. The agents discuss whether it is a legitimate marathon session or a forgotten timer before logging an anomaly report.

Setup guide

Set up Everhour Time Tracking 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 Everhour Time Tracking 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="Everhour Time Tracking_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Everhour Time Tracking 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="Everhour Time Tracking_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Everhour Time Tracking 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 Everhour Time Tracking. 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 Everhour Time Tracking 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 Everhour Time Tracking MCP in AutoGen

Run `pip install -U autogen-ext[mcp]`. Use `mcp_server_tools` with `StreamableHttpServerParams` to fetch the tools, then pass that list directly to your `AssistantAgent` constructor.

Assign the MCP tools to a specialized data-gathering agent. Let this agent fetch the `list_tracked_projects` data and report back to the central conversation rather than giving every agent API access.

Yes. One agent can interpret the raw hours from `list_team_time_records`, while another cross-references those hours against the budget data from `get_project_detailed_data` to argue about project profitability.

Yes. The `McpToolAdapter` automatically converts the JSON schema for tools like `quick_time_tracking_audit` into a format your agents understand, so you do not have to write custom parsers.

No. The MCP Server accesses team member roles and time logs strictly through your authenticated endpoint token. Vinkius processes these requests in a secure, zero-trust sandbox that retains zero state between your agent conversations.

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