How to Use the UtilityAPI MCP in AutoGen

Q: How can AutoGen use UtilityAPI to track usage?

You get the meter UID from listmeters. Then, your AutoGen agents debate whether to run getbills or getintervals first. They converge on using both tools and combining their results for a complete energy picture.

Q: What should I do if I need to test UtilityAPI with AutoGen?

Run createauthform first, then use the resulting form ID in testformsubmission. This simulates a full customer workflow and allows your agents to verify all necessary tools fire correctly.

Q: How do I get started with UtilityAPI using AutoGen?

Start by running listutilities to understand the available providers. Then, use that information to guide one of your initial AutoGen agent prompts.

Build consensus-driven decision systems for AutoGen agents using UtilityAPI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UtilityAPI MCP to AutoGen

Create your Vinkius account to connect UtilityAPI 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 UtilityAPI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Data Retrieval with MCP Server

A complex query might require multiple data sources. Use `get_meter_data` to get the full picture—both billing history and interval readings—and feed that output into AutoGen's debate loop. One agent can calculate cost, while another checks for peak usage from the granular data. This forces consensus among your agents on the most accurate conclusion, making decisions less reliant on a single tool call.

Managing Customer Onboarding via AutoGen

When setting up new utility access, multiple steps are required. An AutoGen system can use `list_utilities` to confirm the correct provider code, then run `create_auth_form`. A third agent can check `get_form_templates` to make sure all necessary data fields were included. The agents debate the setup requirements until they converge on a complete and compliant authorization plan.

Auditing Utility Access with AutoGen

To know who has access, an AutoGen system can coordinate calls to `list_authorizations` and then cross-reference that list against the active meters found via `list_meters`. The agents check for discrepancies or outdated permissions. This structured approach ensures no potential data leak is overlooked, letting you build robust governance workflows.

Setup guide

Set up UtilityAPI 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 UtilityAPI 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="UtilityAPI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You get the meter UID from `list_meters`. Then, your AutoGen agents debate whether to run `get_bills` or `get_intervals` first. They converge on using both tools and combining their results for a complete energy picture.

The server handles utility billing, usage interval data (kWh or therms), and customer authorization records. All this is sensitive financial and consumption data that your AutoGen agents must handle with care.

Yes. The structured, sequential nature of utility data—from listing utilities to creating forms—makes it perfect for multi-agent conversation and decision-making within an AutoGen framework.

Run `create_auth_form` first, then use the resulting form ID in `test_form_submission`. This simulates a full customer workflow and allows your agents to verify all necessary tools fire correctly.

Start by running `list_utilities` to understand the available providers. Then, use that information to guide one of your initial AutoGen agent prompts.

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