How to Use the ClickTime MCP in AutoGen

Q: How do I load ClickTime tools into my AutoGen agents?

Install the autogen-extmcp package. Use the mcpservertools method with StreamableHttpServerParams pointing to your Vinkius URL, then pass that tool list into your AssistantAgent constructor.

Give your AutoGen agents the ability to audit ClickTime hours and debate project budgets via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ClickTime MCP to AutoGen

Create your Vinkius account to connect ClickTime 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 ClickTime with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent AutoGen audits

One agent pulling data is fine, but two agents arguing over it is better. You assign the `list_time_entries` tool from this MCP Server to a Data Analyst agent. That agent pulls the raw hours for a specific week and hands them off to the chat room. A separate Compliance agent reviews those hours against active budgets pulled from `list_clicktime_jobs`. If the Analyst missed a task code, the Compliance agent pushes back and demands a recount. They negotiate until the final report is accurate.

Cross-reference clients and projects

Figuring out billing discrepancies takes serious digging. Your system can trigger `list_clicktime_clients` to grab the master list, then ask another agent to verify the active status via `list_clicktime_projects`. The agents talk to each other to resolve missing links. If a user logged hours to an archived project, the system flags the anomaly before it ever reaches human review.

Automate heavy reporting tasks

Pulling thousands of rows manually crashes browsers. You give your primary agent access to `get_high_volume_time_report`. It fetches up to 2500 records at once and streams the JSON into the shared context. A summarization agent takes over immediately. It parses the payload, groups the hours by the IDs found in `list_clicktime_tasks`, and outputs a clean markdown table for the project manager.

Setup guide

Set up ClickTime 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 ClickTime 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="ClickTime_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the autogen-ext[mcp] package. Use the mcp_server_tools method with StreamableHttpServerParams pointing to your Vinkius URL, then pass that tool list into your AssistantAgent constructor.

Give the tools to a specialized data-fetching agent. Let it execute list_clicktime_users or list_time_entries, and have it report the findings back to a manager agent that lacks API access.

Yes. The McpToolAdapter automatically translates the complex JSON schema required by get_high_volume_time_report into a format the LLM natively understands.

They take turns based on the conversation flow. If the billing agent needs project details, it calls list_clicktime_projects and waits for the response before the next agent speaks.

Security is handled at the transport layer. Vinkius isolates the MCP Server in an ephemeral sandbox, meaning the raw financial data pulled from list_clicktime_jobs is never cached or stored on our infrastructure.

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