How to Use the Buk MCP in AutoGen

Q: How do I register Buk tools with my AutoGen assistant?

You use the mcpservertools helper with your Vinkius HTTP URL to fetch the tools. Pass the resulting list directly into your AssistantAgent constructor to give it execution capabilities.

Q: Can AutoGen agents coordinate to reject a Buk leave request?

Yes, an HR agent can analyze the request fetched via listleaves and argue for rejection. Once the team agrees, they can update the status or notify the employee through your workspace tools.

Deploy AutoGen agent teams to debate, verify, and execute complex Buk HR and payroll workflows automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Buk MCP to AutoGen

Create your Vinkius account to connect Buk 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 Buk with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate and Approve Leave Requests via MCP Server

This MCP Server enables cooperative workflows by exposing `list_leaves` and `approve_leave` to your AutoGen agent groups. A coordinator agent can retrieve pending leaves, while a separate policy agent reviews them against company guidelines before granting approval. This multi-agent debate ensures that no leave request gets approved without checking policy compliance. The agents discuss the request in their chat channel, reach a consensus, and then trigger the write tool to update the system.

Verify Payroll and Company Statistics

The `get_payroll` and `get_company_stats` tools allow your financial agent teams to cross-examine budget allocations. One agent pulls the payroll snapshot while another analyzes overall company statistics to identify spending anomalies. By forcing agents to verify each other's work, you reduce the risk of automated errors. The agents negotiate budget adjustments in real-time, only finalizing reports when both agree the calculations are accurate.

Collaborative Employee Onboarding

You can coordinate complex hiring tasks using `create_employee` and `list_benefits` across specialized agent roles. An onboarding agent creates the profile, while a benefits coordinator agent assigns the correct corporate extras to the new hire. This cooperative structure prevents data entry errors during high-volume hiring periods. The agents communicate back and forth to confirm that every required benefit field is populated before finalizing the onboarding process.

Setup guide

Set up Buk 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 Buk 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="Buk_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You use the mcp_server_tools helper with your Vinkius HTTP URL to fetch the tools. Pass the resulting list directly into your AssistantAgent constructor to give it execution capabilities.

Yes, an HR agent can analyze the request fetched via list_leaves and argue for rejection. Once the team agrees, they can update the status or notify the employee through your workspace tools.

Yes, the adapter handles streamable HTTP connections out of the box. You simply provide the endpoint URL, and the adapter translates the schemas for your agent conversations.

The agents discuss the discrepancies in their chat log, using tools like get_employee to fetch ground-truth data. They resolve the conflict through dialogue before executing any write actions.

Vinkius never stores your payroll records or leave requests; it merely proxies the MCP Server tool calls through ephemeral sandboxes. Your data remains securely inside your platform, protected by industry-standard encryption.

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