How to Use the OpenEI MCP in AutoGen

Q: How do I configure AutoGen to use the OpenEI MCP server?

Install autogen-extmcp and use mcpservertools with a StreamableHttpServerParams configuration. Pass the resulting tool list directly into your AssistantAgent constructor.

Q: How do AutoGen agents handle missing addresses in OpenEI?

If getratesbyaddress fails, a well-prompted agent will automatically pivot to using getratesbycoordinates. They discuss the failure in the chat and formulate a backup plan using alternative tools.

Deploy AutoGen multi-agent debates to analyze OpenEI utility rates and negotiate the most profitable solar project designs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect OpenEI MCP to AutoGen

Create your Vinkius account to connect OpenEI 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 OpenEI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debate utility selection with AutoGen

`list_utilities` and `search_utilities_by_name` feed raw company data to your researcher agent. This agent pulls the available utilities for a region and proposes a target operator. A secondary compliance agent verifies the service territory before the system proceeds to rate analysis. Hitting `get_utility_detail` gives the agents the generation mix and contact info required to evaluate a utility's solar friendliness. They negotiate the viability of the market based on this data. You watch the agents argue over jurisdiction boundaries instead of doing the manual research yourself.

Evaluate complex tariffs using the MCP Server

`get_rate_detail` provides the complete list of demand charges and seasonal variations that make or break a project. A financial agent pulls this data, while a risk agent challenges the assumptions about time-of-use periods. They iterate on the math until they agree on a conservative cost projection. Your system uses `get_residential_rates` to model homeowner savings. The proposal agent drafts a pitch based on the tiered rates, and the critical agent forces revisions if the ROI looks suspiciously high. The final output represents a consensus built on hard API data.

Analyze commercial sites autonomously

`get_rates_by_address` and `get_rates_by_coordinates` allow the agents to pinpoint exact tariffs for specific parcels of land. The site selection agent feeds coordinates into the tools and receives the applicable commercial or industrial rates. This triggers a debate over whether the location has favorable demand charges. Running `get_commercial_rates` and `get_industrial_rates` exposes the heavy-duty tariffs needed for large-scale modeling. The engineering agent uses the power factor adjustments to size the inverter, while the finance agent calculates the payback period. They work together to optimize the system design against the actual utility billing structure.

Setup guide

Set up OpenEI 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 OpenEI 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="OpenEI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use `mcp_server_tools` with a `StreamableHttpServerParams` configuration. Pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes. You provide the tool list to any agent that needs it, like a rate analyst or a site selector. The `McpToolAdapter` automatically converts the JSON schemas into a format the agents understand.

If `get_rates_by_address` fails, a well-prompted agent will automatically pivot to using `get_rates_by_coordinates`. They discuss the failure in the chat and formulate a backup plan using alternative tools.

Your coordinator agent assigns different states to parallel researcher agents. They use `get_utility_rates` to pull the data and then converge in a group chat to debate which market offers the best industrial tariffs.

Target street addresses and utility IDs pass through a zero-trust V8 isolate environment. The endpoint calculates the service territory, returns the rate structures, and wipes the memory state. Vinkius prevents any persistence of your locational 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