Which US electricity grid operators (ISOs) are supported?

The GridStatus API supports all major US Independent System Operators: ERCOT (Texas), CAISO (California), PJM (Mid-Atlantic/Midwest), MISO (Midwest), NYISO (New York), ISO-NE (New England), and SPP (Southwest/Central). Each ISO provides different datasets including load, fuel mix, LMP pricing, and standardized data depending on what they report.

How do I get a GridStatus API key and what are the usage limits?

Visit https://www.gridstatus.io/ and create a free account. Your API key will be available in your account settings. The free tier includes 500,000 rows per month, which is sufficient for most research and analysis use cases. Use the `get_api_usage` tool to monitor your remaining quota. Higher tiers are available for commercial applications requiring more data access.

What is the difference between LMP and SPP pricing data?

LMP (Locational Marginal Pricing) is used by most ISOs (PJM, CAISO, MISO, NYISO, ISO-NE, SPP) and represents the wholesale electricity price at specific nodes. SPP (Settlement Point Price) is ERCOT's equivalent for Texas. Both measure $/MWh but use different market mechanisms. LMP has day-ahead hourly and real-time 5-minute intervals. ERCOT SPP has day-ahead hourly and real-time 15-minute intervals. Both include prices at trading hubs (e.g. HB_HOUSTON, HB_NORTH), load zones, and resource zones.

Can I get renewable energy percentage data from the fuel mix?

Yes! Use the `get_fuel_mix` tool with ISOs that support it (ERCOT, CAISO, ISO-NE). The response includes generation breakdown by source: solar, wind, hydro, natural_gas, coal, nuclear, and others. You can calculate the renewable percentage by summing solar + wind + hydro and dividing by total generation. Note that fuel mix data availability varies by ISO — ERCOT and CAISO have the most comprehensive renewable tracking.

GridStatus MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes

Name: GridStatus
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 12 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect GridStatus through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="GridStatus Assistant",
            instructions=(
                "You help users interact with GridStatus. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from GridStatus"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About GridStatus MCP Server

Connect to GridStatus.io API and bring comprehensive US electricity market intelligence to any AI agent. Monitor all major Independent System Operators (ISOs), track renewable energy transition, analyze wholesale prices, and understand grid dynamics across America.

The OpenAI Agents SDK auto-discovers all 12 tools from GridStatus through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries GridStatus, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Electricity Load/Demand — Retrieve real-time and historical electricity consumption data (MW) for any US ISO region
Fuel Mix & Generation — Get breakdown of power generation by source (coal, natural gas, nuclear, solar, wind, hydro) to understand the energy mix
Day-Ahead LMP Pricing — Access hourly Locational Marginal Pricing forecasts for specific nodes and trading hubs across ISOs
Real-Time 5-Minute LMP — Track live wholesale electricity prices at 5-minute intervals to identify price spikes and volatility
ERCOT SPP Data — Query Settlement Point Prices for Texas grid including day-ahead hourly and real-time 15-minute intervals at trading hubs
Standardized Zonal Data — Fetch consistently formatted hourly data with regional/zonal breakdowns for modeling and analysis
Capacity Markets — Monitor capacity commitments and resource adequacy data for long-term planning
Dataset Exploration — List all available datasets, check metadata including coverage dates and available columns
API Usage Tracking — Monitor your API quota usage, row counts, and rate limits
Custom Dataset Queries — Query any dataset with advanced filtering, resampling, and aggregation controls
Multi-ISO Coverage — Access data from ERCOT (Texas), CAISO (California), PJM (Mid-Atlantic), MISO (Midwest), NYISO (New York), ISO-NE (New England), and SPP (Southwest)

The GridStatus MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect GridStatus to OpenAI Agents SDK via MCP

Follow these steps to integrate the GridStatus MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 12 tools from GridStatus

Why Use OpenAI Agents SDK with the GridStatus MCP Server

OpenAI Agents SDK provides unique advantages when paired with GridStatus through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

GridStatus + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the GridStatus MCP Server delivers measurable value.

Automated workflows: build agents that query GridStatus, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries GridStatus, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through GridStatus tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query GridStatus to resolve tickets, look up records, and update statuses without human intervention

GridStatus MCP Tools for OpenAI Agents SDK (12)

These 12 tools become available when you connect GridStatus to OpenAI Agents SDK via MCP:

get_api_usage

Shows how many rows you've queried and your remaining allowance. USE WHEN: - User asks about their API usage or quota - User wants to check how many rows they have remaining - User needs to verify their rate limits - User asks about their GridStatus account status EXAMPLES: - "How much API quota do I have left?" → call with no params - "Check my API usage this month" → call with no params - "Show my rate limits" → call with no params Get API usage statistics and rate limits for your GridStatus account

get_capacity_data

This data is used to track long-term resource adequacy and capacity commitments. USE WHEN: - User asks about generation capacity or capacity markets - User needs capacity commitment data for an ISO - User wants to track resource adequacy metrics - User asks about capacity prices or availability SUPPORTED ISOs: - pjm (primary capacity market), others may be available PARAMETERS: - iso (REQUIRED): ISO identifier - start (OPTIONAL): Start date - end (OPTIONAL): End date - limit (OPTIONAL): Maximum rows EXAMPLES: - "PJM capacity data for next month" → call with iso="pjm", start="2026-05-01" - "Show capacity commitments" → call with iso="pjm" Get capacity market data for a US ISO

get_dataset_metadata

USE WHEN: - User wants to know the date range covered by a dataset - User needs to see what columns are available in a dataset - User asks about data frequency or schema for a specific dataset - User is validating if a dataset exists before querying PARAMETERS: - dataset_id (REQUIRED): Dataset identifier (e.g. "pjm_load", "ercot_fuel_mix", "caiso_lmp_day_ahead_hourly") EXAMPLES: - "Show metadata for PJM load dataset" → call with dataset_id="pjm_load" - "What columns are in ERCOT fuel mix?" → call with dataset_id="ercot_fuel_mix" - "Date range for CAISO LMP" → call with dataset_id="caiso_lmp_day_ahead_hourly" Get metadata for a specific GridStatus dataset

get_fuel_mix

) for any supported US ISO. Essential for understanding where electricity comes from and tracking the renewable energy transition. USE WHEN: - User asks about the energy mix or generation breakdown - User wants to know how much power comes from solar, wind, coal, etc. - User asks about renewable energy percentage - User needs to compare fossil vs clean energy generation SUPPORTED ISOs WITH FUEL MIX: - ercot (Texas), caiso (California), isone (New England) PARAMETERS: - iso (REQUIRED): ISO identifier: ercot, caiso, or isone - start (OPTIONAL): Start date - end (OPTIONAL): End date - limit (OPTIONAL): Maximum rows - timezone (OPTIONAL): Timezone for results EXAMPLES: - "What is Texas energy mix right now?" → call with iso="ercot", start="latest" - "Show Californiaia renewable generation today" → call with iso="caiso", start="2026-04-07" - "New England fuel mix this week" → call with iso="isone", start="2026-04-01", limit=168 Get electricity generation by fuel source (energy mix) for a US ISO

get_lmp_data

LMP is measured in dollars per megawatt-hour ($/MWh). USE WHEN: - User asks about wholesale electricity prices at specific locations - User needs day-ahead price forecasts for an ISO - User wants to compare prices across different nodes - User asks about LMP or nodal pricing data SUPPORTED ISOs WITH LMP: - pjm (Mid-Atlantic), caiso (California), miso (Midwest), nyiso (New York), isone (New England), spp (Southwest) PARAMETERS: - iso (REQUIRED): ISO identifier: pjm, caiso, miso, nyiso, isone, or spp - start (OPTIONAL): Start date - end (OPTIONAL): End date - limit (OPTIONAL): Maximum rows - timezone (OPTIONAL): Timezone for results - filter_column (OPTIONAL): Column to filter on (e.g. "location") - filter_value (OPTIONAL): Value to filter by EXAMPLES: - "Show PJM day-ahead LMP for tomorrow" → call with iso="pjm", start="2026-04-08" - "CAISO LMP at SP15 node today" → call with iso="caiso", start="2026-04-07", filter_column="location", filter_value="SP15" - "MISO hourly prices this week" → call with iso="miso", start="2026-04-01", limit=168 Get day-ahead Locational Marginal Pricing (LMP) data for a US ISO

get_load_data

Shows how much electricity is being consumed across the grid region. USE WHEN: - User asks about electricity demand or consumption for an ISO - User needs load data for a specific time period - User wants to compare load across different regions - User asks how much electricity is being used in Texas, California, etc. SUPPORTED ISOs: - ercot (Texas), caiso (California), pjm (Mid-Atlantic), miso (Midwest) - nyiso (New York), isone (New England), spp (Southwest) PARAMETERS: - iso (REQUIRED): ISO identifier (lowercase): ercot, caiso, pjm, miso, nyiso, isone, spp - start (OPTIONAL): Start date in YYYY-MM-DD or ISO 8601 format - end (OPTIONAL): End date in YYYY-MM-DD or ISO 8601 format - limit (OPTIONAL): Maximum number of rows to return (default varies by plan) - timezone (OPTIONAL): Timezone for results ("market" for ISO local time, or standard like "US/Eastern") EXAMPLES: - "What is current electricity demand in Texas?" → call with iso="ercot", start="latest" - "Show PJM load for yesterday" → call with iso="pjm", start="2026-04-06", end="2026-04-07" - "California load data this week" → call with iso="caiso", start="2026-04-01", limit=168 Get electricity load/demand data for a specific US ISO

get_realtime_lmp

This is the most granular and up-to-date pricing data available. USE WHEN: - User asks about current/real-time electricity prices - User needs 5-minute interval price data - User wants to track price spikes or volatility in real-time - User asks about live nodal pricing SUPPORTED ISOs: - pjm, caiso, miso, nyiso, isone, spp PARAMETERS: - iso (REQUIRED): ISO identifier - start (OPTIONAL): Start date/time (use "latest" for most recent) - end (OPTIONAL): End date/time - limit (OPTIONAL): Maximum rows (recommended to limit real-time data) - timezone (OPTIONAL): Timezone EXAMPLES: - "Current real-time LMP in PJM" → call with iso="pjm", start="latest", limit=12 - "CAISO 5-min prices right now" → call with iso="caiso", start="latest", limit=12 - "Last hour of real-time MISO prices" → call with iso="miso", start="latest", limit=12 Get real-time 5-minute LMP data for a US ISO

get_realtime_spp

Shows the most current wholesale electricity prices at trading hubs and zones in the Texas grid. USE WHEN: - User asks about current/real-time Texas electricity prices - User needs 15-minute interval SPP data for ERCOT - User wants to track price spikes or negative pricing in Texas - User asks about live ERCOT hub prices PARAMETERS: - start (OPTIONAL): Start date/time (use "latest" for most recent) - end (OPTIONAL): End date/time - limit (OPTIONAL): Maximum rows (recommended for real-time data) - timezone (OPTIONAL): Timezone EXAMPLES: - "Current ERCOT SPP at Houston hub" → call with start="latest", limit=4, filter_column="Settlement Point", filter_value="HB_HOUSTON" - "Last hour of Texas real-time prices" → call with start="latest", limit=4 - "ERCOT West hub prices today" → call with start="2026-04-07", filter_column="Settlement Point", filter_value="HB_WEST" Get ERCOT real-time 15-minute Settlement Point Price (SPP) data

get_spp_data

SPP is similar to LMP but specific to ERCOT's market design, showing prices at trading hubs, load zones, and resource zones. USE WHEN: - User asks about ERCOT electricity prices or SPP - User needs day-ahead price forecasts for Texas - User wants prices at specific ERCOT trading hubs (e.g. HB_HOUSTON, HB_NORTH, HB_WEST) - User asks about Texas wholesale electricity market prices PARAMETERS: - start (OPTIONAL): Start date - end (OPTIONAL): End date - limit (OPTIONAL): Maximum rows - timezone (OPTIONAL): Timezone (ERCOT uses US/Central) - filter_column (OPTIONAL): Column to filter (e.g. "Settlement Point") - filter_value (OPTIONAL): Hub/zone name to filter by EXAMPLES: - "ERCOT SPP for Houston hub tomorrow" → call with start="2026-04-08", filter_column="Settlement Point", filter_value="HB_HOUSTON" - "Texas day-ahead prices today" → call with start="2026-04-07" - "ERCOT SPP this week at North hub" → call with start="2026-04-01", filter_column="Settlement Point", filter_value="HB_NORTH" Get ERCOT Settlement Point Price (SPP) day-ahead hourly data

get_standardized_data

Useful for zonal/regional breakdowns of load, generation, or pricing with uniform schema across time periods. USE WHEN: - User needs consistently formatted hourly data for analysis - User asks for zonal or regional breakdowns - User wants standardized data for cross-ISO comparisons - User needs clean data for modeling or visualization SUPPORTED ISOs: - pjm (extensive zonal data), caiso, miso, others PARAMETERS: - iso (REQUIRED): ISO identifier - start (OPTIONAL): Start date - end (OPTIONAL): End date - limit (OPTIONAL): Maximum rows - timezone (OPTIONAL): Timezone EXAMPLES: - "PJM zonal load for today" → call with iso="pjm", start="2026-04-07" - "Standardized CAISO data this week" → call with iso="caiso", start="2026-04-01", limit=168 - "PJM hourly load yesterday" → call with iso="pjm", start="2026-04-06", end="2026-04-07" Get standardized hourly data for a US ISO with consistent column naming

list_datasets

Shows dataset identifiers, coverage dates, and available columns. USE WHEN: - User wants to explore what data is available in GridStatus - User needs to find dataset identifiers for querying - User is exploring the API capabilities for the first time - User asks what ISOs and data types are supported SUPPORTED ISOS: - ERCOT (Texas), CAISO (California), PJM (Mid-Atlantic/Midwest) - MISO (Midwest), NYISO (New York), ISO-NE (New England), SPP (Southwest) DATASET TYPES: - load (electricity demand), fuel_mix (generation by source) - lmp (locational marginal pricing), spp (settlement point prices) - capacity, standardized data EXAMPLES: - "What datasets are available?" → call with no params - "Show me all dataset identifiers" → call with no params - "List all supported ISOs" → call with no params List all available datasets in the GridStatus API

query_dataset

Use this when specific data needs are not covered by the specialized tools. USE WHEN: - User needs data from a specific dataset not covered by other tools - User wants custom filtering or resampling - User has a specific dataset identifier and needs flexible querying - User needs advanced filter operators PARAMETERS: - dataset_id (REQUIRED): Full dataset identifier (e.g. "pjm_load", "ercot_fuel_mix") - start (OPTIONAL): Start date - end (OPTIONAL): End date - limit (OPTIONAL): Maximum rows - timezone (OPTIONAL): Timezone for results - filter_column (OPTIONAL): Column name to filter on - filter_value (OPTIONAL): Value to filter by - filter_operator (OPTIONAL): Filter operator (=, !=, >, <, >=, <=, in) - resample (OPTIONAL): Resampling interval (e.g. "1 hour", "1 day") - resample_function (OPTIONAL): Aggregation function (mean, sum, min, max) EXAMPLES: - "Query pjm_load for last week" → call with dataset_id="pjm_load", start="2026-03-31", limit=168 - "ERCOT fuel mix resampled daily" → call with dataset_id="ercot_fuel_mix", start="2026-04-01", resample="1 day", resample_function="mean" - "CAISO load filtered for SDGE zone" → call with dataset_id="caiso_load", start="2026-04-07", filter_column="location", filter_value="SDGE" Query any GridStatus dataset with custom filters and parameters

Example Prompts for GridStatus in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with GridStatus immediately.

"What is the current electricity demand in ERCOT (Texas)?"

"Show me the energy mix for California right now — how much comes from solar, wind, and natural gas?"

"What are day-ahead electricity prices for the PJM Houston hub tomorrow?"

Troubleshooting GridStatus MCP Server with OpenAI Agents SDK

Common issues when connecting GridStatus to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

GridStatus + OpenAI Agents SDK FAQ

Common questions about integrating GridStatus MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.