How to Use the ClockShark MCP in AutoGen

Q: How do I give ClockShark tools to an AutoGen agent?

You'll use the autogen-extmcp package. The mcpservertools function takes your Vinkius server URL and returns a list of tools that you can pass directly to an AssistantAgent during its initialization.

Q: Is it possible for AutoGen agents to schedule shifts in ClockShark?

Definitely. You can have a 'Scheduler' agent use the createshift tool. A powerful pattern is to pair it with a 'Validator' agent that uses listschedules to check for conflicts before the shift is finalized.

Let AutoGen agent teams debate and manage your ClockShark scheduling and job costing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ClockShark MCP to AutoGen

Create your Vinkius account to connect ClockShark 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 ClockShark with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate the Weekly Schedule

This is where AutoGen shines. You can create a team of agents to build a schedule. One agent, the 'Planner', proposes a new schedule by calling `create_shift`. A second agent, the 'Auditor', immediately checks for conflicts using `list_schedules` and `get_employee_details`. They converse until they reach a consensus on a valid schedule that respects everyone's availability and avoids overtime. The final output is a schedule that's already been vetted by multiple perspectives.

Plan Projects with Agent Teams

Have a 'Planner' agent `create_job` and then use `create_task` to outline the project's phases. At the same time, a 'Finance' agent can `list_timesheets` from similar past jobs to project costs and flag potential budget overruns. These agents debate the project plan in a recorded conversation. They refine the scope and budget based on historical data from your ClockShark account before you've assigned a single task. This MCP server provides the facts for their discussion.

An AutoGen Team for Timesheet Audits

Set up an autonomous system for payroll verification. One agent's job is to pull all recent time entries using `list_timesheets`. A second agent's role is to verify each entry against active projects by calling `list_jobs` and `list_tasks`. If the 'Auditor' agent finds a timesheet logged against a closed or non-existent job, it flags the entry and brings it to the attention of the 'Manager' agent (or a human). It’s an automated, conversational check-and-balance system.

Setup guide

Set up ClockShark 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 ClockShark 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="ClockShark_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You'll use the `autogen-ext[mcp]` package. The `mcp_server_tools` function takes your Vinkius server URL and returns a list of tools that you can pass directly to an `AssistantAgent` during its initialization.

Yes, that's a core use case. You can create one agent responsible for planning (`create_job`, `create_task`) and another for financial oversight that uses tools like `list_timesheets` to ground the plan in historical data.

Authentication is managed by the Vinkius platform. You provide your unique server URL, which includes your token, to the AutoGen MCP extension. The extension handles passing the correct headers for each tool call automatically.

Definitely. You can have a 'Scheduler' agent use the `create_shift` tool. A powerful pattern is to pair it with a 'Validator' agent that uses `list_schedules` to check for conflicts before the shift is finalized.

Your employee, schedule, and timesheet data is only accessed for the duration of a tool call. Each operation from your AutoGen agent runs in a dedicated, single-use sandbox on Vinkius. The data is never stored, and the environment is disposed of once the task is complete.

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