How to Use the Pennylane MCP in AutoGen

Build debating agents in AutoGen to verify and reconcile Pennylane accounting entries through multi-agent consensus.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pennylane MCP to AutoGen

Create your Vinkius account to connect Pennylane to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pennylane with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debate accounting logic in AutoGen

Assign one agent to draft invoices using `create_customer` and another to audit the entry. They negotiate until the data matches your compliance standards. This prevents errors before they hit your ledger. Your agents cross-reference `list_customer_invoices` to ensure no duplicate entries exist.

Manage Pennylane MCP Server with agents

Your security agent can monitor `list_suppliers` for anomalies while your finance agent manages payments. They discuss potential risks before finalizing any transaction. This multi-agent approach provides a layer of oversight. You define the rules, and the agents verify the data against them.

Consensus-driven financial records

Agents reach agreement on complex categorizations. By calling `list_categories`, they ensure every `create_product` entry follows your internal accounting taxonomy. This removes the guesswork from ledger entry. Your agents rely on the explicit schema provided by the tools to maintain consistency.

Setup guide

Set up Pennylane 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 Pennylane 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="Pennylane_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Agents pass tool outputs back and forth in their conversation. One agent calls `get_customer_details` and shares the result with the auditor agent for verification.

Yes, by orchestrating a sequence of tool calls. Agents can list estimates, create customers, and finalize invoices through collaborative deliberation.

We use a single endpoint token for your server. Your agents operate only within the scope allowed by your Pennylane credentials, ensuring data privacy.

They will continue to debate until they reach a conclusion you've defined. You can set a limit on the number of turns to prevent infinite loops.

You can configure an auditor agent to inspect every invoice created. It uses `get_customer_invoice_details` to check for tax compliance before confirming the record.

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