How to Use the everbill MCP in AutoGen

Q: Can one AutoGen agent create an everbill customer and another bill them?

Yes, that's exactly how it's designed to work. You'd give createcustomer to an "Onboarding" agent and createinvoice to a "Billing" agent, and they would coordinate in a chat before acting.

Set up a team of AutoGen agents to debate, manage, and execute your freelance accounting tasks using this everbill server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect everbill MCP to AutoGen

Create your Vinkius account to connect everbill 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 everbill with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Your Agents Are In Charge

This MCP Server gives your AutoGen agents the tools they need to run your billing. One agent can propose creating an invoice, while another acts as a verifier, using `get_customer` to double-check the client's status before giving the go-ahead. You aren't just running a script; you're simulating a team. The agents converse, passing data from `list_products` or `list_invoices` between each other to reach a consensus before any action is taken. This is how you reduce errors.

Automated Client Onboarding

When a new client project starts, kick off an AutoGen conversation. One agent can use `create_customer` to add them to everbill, while a project manager agent confirms the details. A third agent could then use `create_invoice` to set up the initial deposit invoice. Each agent has a role, and they use the everbill tools to do their job. You just watch the conversation and approve the final plan. It's a safer way to automate complex financial workflows.

The AutoGen MCP Server

This isn't about one agent making a call. It's about building a system of checks and balances for your finances. You can have one agent responsible for pulling data with `list_invoices`, and a separate "auditor" agent that only has permission to view data with `get_invoice` to verify the work. AutoGen's multi-agent model, combined with this MCP server, lets you build robust financial processes. You can create specialized agents that use `get_customer` or `list_products` to ensure every invoice created by `create_invoice` is perfect.

Setup guide

Set up everbill 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 everbill 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="everbill_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You assign tools to different agents. For example, a "BillingClerk" agent might have the `create_invoice` tool, and it will use it when instructed by a "Manager" agent after they agree on a plan.

Yes, that's exactly how it's designed to work. You'd give `create_customer` to an "Onboarding" agent and `create_invoice` to a "Billing" agent, and they would coordinate in a chat before acting.

You use multiple agents for checks and balances. Have one agent propose an action, like using `create_invoice`, and require a second "Auditor" agent to confirm the details with `get_customer` before it's executed.

The conversation log in AutoGen is your audit trail. You can see which agent decided to call `list_invoices`, what it found, and how the other agents reacted to that information before making a decision.

The MCP server manages the secure connection to everbill. When your AutoGen agents use a tool, the specific data for that request—like customer names or invoice amounts—is passed through our ephemeral, zero-trust platform. We don't log or keep your business data.

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