How to Use the KeyPay MCP in AutoGen

Q: How do I register KeyPay tools with an AutoGen agent?

You use the mcpservertools helper to load the tools from the Vinkius HTTP endpoint. Pass the resulting tool list directly to your AssistantAgent constructor so the agent can invoke listpayruns.

Build multi-agent AutoGen teams that debate and verify payroll records using the KeyPay 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 KeyPay MCP to AutoGen

Create your Vinkius account to connect KeyPay 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 KeyPay with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent payroll verification loops

Your AutoGen agents collaborate using `get_pay_run_details` and `list_pay_run_deductions` to audit payroll calculations before finalizing them. One agent pulls the pay run details, while a second agent inspects the deductions for anomalies. That's the catch: these agents debate the results in a group chat, challenging unexpected variances or missing deduction codes. This consensus-driven approach ensures that payroll errors are caught and resolved before any funds leave your account.

Consensus-driven employee onboarding checks

Verifying new hire setups requires checking data across `list_employees` and `get_employee_details` before running payroll. A compliance agent verifies tax configurations, while an operations agent checks bank details. Using AutoGen's conversational patterns, the two agents negotiate whether the employee profile is complete. They will block pay run inclusion until both agents agree that all mandatory fields are correctly configured.

Automated pay slip auditing via the MCP Server

Auditing individual worker earnings relies on analyzing `list_pay_slips` alongside `list_pay_run_earnings`. The finance agent compares the generated payslip totals against the raw earnings logs to detect mismatches. This validation occurs within a structured conversation where the auditor agent demands clarification from the payroll processor agent. Only when both agents reconcile the numbers does the system flag the pay slip as verified.

Setup guide

Set up KeyPay 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 KeyPay 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="KeyPay_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You use the mcp_server_tools helper to load the tools from the Vinkius HTTP endpoint. Pass the resulting tool list directly to your AssistantAgent constructor so the agent can invoke list_pay_runs.

Yes, multiple agents in a group chat can call endpoints like list_employees or get_business_details. The Vinkius sandbox handles the concurrent requests safely using isolated execution threads.

The agents debate the discrepancies using their respective system prompts. For example, a budget agent might flag high earnings from list_pay_run_earnings, prompting a manager agent to verify the run.

The MCP adapter supports both stdio and Streamable HTTP transports. For production multi-agent systems, the HTTP transport is recommended to keep agents decoupled from the local terminal environment.

The integration employs strict end-to-end encryption for all payload transfers, ensuring that sensitive financial records and bank codes are never cached. Vinkius operates on a zero-trust model where execution environments are destroyed immediately after execution.

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