How to Use the OpenEI MCP in CrewAI

Q: How do I configure OpenEI tools for a CrewAI agent?

Pass your Vinkius server URL directly into the agent's mcps array. The framework automatically registers the MCP tools so your specialized agents can query electricity rates.

Q: Can I restrict which OpenEI tools a specific CrewAI agent can use?

Yes, use the MCPServerHTTP class with a toolfilter to expose only selected tools. This lets you give your research agent listutilities while keeping getratedetail restricted to your analyst agent.

Deploy a crew of specialized energy agents using CrewAI and the OpenEI MCP server.

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 CrewAI

Create your Vinkius account to connect OpenEI to CrewAI — 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Run multi-agent utility rate analysis with CrewAI

The `get_utility_rates` tool lets your research agent pull raw tariff options for any location. In a CrewAI setup, this agent handles the initial database search while a separate analyst agent parses the output to calculate seasonal averages. This division of labor mimics a human energy consulting team, producing highly accurate feasibility reports. You set this up by passing your Vinkius server URL directly into the agent's `mcps` list. The MCP Server framework handles tool discovery and exposes the endpoints to your crew automatically.

Audit commercial energy bills autonomously

The `get_rate_detail` tool provides the deep tariff breakdowns needed for commercial bill auditing. Your auditor agent can query this tool to dissect demand charges, while a coordinator agent matches those rules against actual customer usage logs. This automated audit flags billing discrepancies without human intervention. This multi-agent collaboration reduces the time it takes to review commercial accounts. The agents share memory, allowing them to pass complex JSON rate structures back and forth without losing context.

Locate service territories across disjointed databases

The `search_utilities_by_name` tool allows your crew to match messy customer utility names to official company records. When a customer inputs an abbreviation, your search agent resolves the official name and passes the ID to a second agent running `get_utility_detail`. This workflow ensures your system always maps the correct service territory. This setup eliminates manual data cleaning. Your crew of agents works sequentially to resolve ambiguous inputs and retrieve precise operational data.

Setup guide

Set up OpenEI MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke OpenEI tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="OpenEI Analyst",
    goal="Access and analyze OpenEI data via MCP.",
    backstory="Expert analyst with direct OpenEI access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent OpenEI transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="OpenEI Analyst",
        goal="Access and analyze OpenEI data via MCP.",
        backstory="Expert analyst with direct OpenEI access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent OpenEI transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass your Vinkius server URL directly into the agent's `mcps` array. The framework automatically registers the MCP tools so your specialized agents can query electricity rates.

Yes, use the `MCPServerHTTP` class with a `tool_filter` to expose only selected tools. This lets you give your research agent `list_utilities` while keeping `get_rate_detail` restricted to your analyst agent.

Agents use shared memory to pass the JSON output of tools like `get_commercial_rates` between tasks. The analyst agent reads the raw rate data retrieved by the research agent to calculate ROI.

The framework supports stdio, SSE, and Streamable HTTP. For cloud deployments, the Streamable HTTP transport provides the most reliable connection to your Vinkius MCP Server.

Your tariff requests are isolated within transient Vinkius execution environments that destroy all session data immediately after the crew finishes its run. No coordinates or utility names are ever stored or used for training models.

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