PG&E Data Portals MCP. Pinpoint local grid capacity and consumption trends.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
PG&E Data Portals connects your AI client directly to PG&E's public energy datasets. Query electricity usage, solar generation capacity, and EV adoption trends by ZIP code and date range.
Use this server to programmatically analyze grid infrastructure data for planning, research, or market analysis.
What your AI agents can do
Get dataset schema
Shows the column names and data types for a specific PG&E dataset ID.
List all datasets
Returns a list of all available datasets, including energy usage, solar, EV adoption, and grid infrastructure.
Query by date range
Retrieves records from any dataset that fall within specified start and end dates for trend analysis.
Lists every dataset PG&E tracks—including usage, solar, and grid data—so you know exactly where to look.
Retrieves the schema (columns and data types) for any specific PG&E dataset ID before running a query.
Gets electricity or gas usage records, filtered precisely by ZIP code and date range.
Retrieves electric vehicle registration counts and adoption rates for specific ZIP codes and years.
Accesses distribution circuit, substation data, and general grid capacity metrics by region.
Gathers solar generation statistics (like installed capacity or net energy metering) for a specific county or service area.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
PG&E Data Portals MCP Server: 10 Tools for Energy Analytics
These tools give your AI client programmatic access to PG&E's public energy datasets, allowing you to query usage patterns, grid capacity, and adoption rates without manual API calls.
019d75f1get dataset schema
Shows the column names and data types for a specific PG&E dataset ID.
019d75f1list all datasets
Returns a list of all available datasets, including energy usage, solar, EV adoption, and grid infrastructure.
019d75f1query by date range
Retrieves records from any dataset that fall within specified start and end dates for trend analysis.
019d75f1query dataset
Queries a specific PG&E dataset using key-value filters like zip code or region to get data records.
019d75f1query energy efficiency
Gets program results and savings amounts for energy efficiency initiatives, filtered by year and program type.
019d75f1query energy usage
Queries electricity or gas consumption data broken down by customer segment (e.g., residential) and ZIP code.
019d75f1query ev adoption
Retrieves electric vehicle registration counts, showing adoption rates for specific ZIP codes and years.
019d75f1query grid infrastructure
Queries data on distribution circuits, substations, and grid capacity by region or infrastructure type.
019d75f1query solar generation
Gathers solar energy production statistics (capacity/production) for a specific county or service area in a given year.
019d75f1search datasets
Searches the PG&E catalog using keywords to discover relevant datasets before running a full query.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with PG&E Data Portals, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Listen up. This server hooks your agent right into PG&E’s public energy data portals. It's not some slick, vague dashboard; it gives you programmatic access to actual usage patterns, solar capacity figures, and grid infrastructure details. You don't gotta mess with manual downloads or weird web forms—your AI client just uses structured tools to get exactly what you need.
Finding Your Data
If you're not sure where the info lives, start by listing everything available using list_all_datasets; this shows every dataset PG&E tracks, from usage numbers to EV adoption rates. You can refine that search with search_datasets if you know a keyword but don't know the ID. Before running any query, you gotta check the structure; use get_dataset_schema by plugging in a specific PG&E dataset ID.
This tells you all the column names and data types, so you never waste time on a bad query.
Pulling General Data & Trends
You can pull records from any dataset that fall between two dates using query_by_date_range for trend analysis. For general querying when you know what you're looking for, run query_dataset, letting the tool filter by key-value pairs like a specific ZIP code or region.
Analyzing Energy Use and Efficiency
To check electricity or gas consumption data, use query_energy_usage. You can get records broken down specifically by customer segment—say, residential—and filtered precisely by ZIP code. If you're tracking energy efficiency programs, query_energy_efficiency gets you the program results and estimated savings amounts, letting you narrow it down by year or specific program type.
Tracking Renewables and Grid Health
For solar power, query_solar_generation collects statistics on production—like installed capacity or net energy metering—for a defined county or service area in a given year. If you need to assess the physical grid, query_grid_infrastructure pulls data on distribution circuits, substations, and overall grid capacity metrics, letting you filter by region or infrastructure type.
These tools let you map out where the power actually runs.
Mobility and Consumption Analysis
Need to track electric vehicles? query_ev_adoption retrieves EV registration counts, showing adoption rates for specific ZIP codes across years. For a comprehensive view of consumption, you can use query_energy_usage or look at solar metrics with query_solar_generation. These tools let you programmatically analyze everything from how many cars are electric to how much power the grid actually supports.
It's built for the guy who needs reliable, structured access to time-series energy data. You don't waste time on guesswork; your agent just pulls the numbers straight out.
How PG&E Data Portals MCP Works
- 1 First, use
list_all_datasetsto see the full catalog of available PG&E data. - 2 Next, run
get_dataset_schemaon a promising dataset ID. This lets you confirm the exact field names and acceptable values (e.g., 'ZIP code' or 'Region'). - 3 Finally, execute a specific tool like
query_energy_usage, passing the required parameters (ID, ZIP code, dates) to get clean data records.
The bottom line is: it lets you build complex energy reports using simple chat prompts instead of manual API calls or spreadsheet merging.
Who Is PG&E Data Portals MCP For?
Energy Analysts, Urban Planners, and Researchers need this. If your job involves forecasting infrastructure needs or modeling climate impact, you'll hit data walls quickly. This server lets you bypass the portal UI and query structured energy metrics directly from your agent.
Tracks historical electricity and gas usage patterns by segment (residential/commercial) to identify peak consumption times or areas needing efficiency upgrades.
Checks regional grid infrastructure data against proposed developments to ensure local capacity can handle new demands, like EV charging stations.
Runs time-series queries on solar generation and EV adoption across multiple ZIP codes to build academic models of clean energy transition.
What Changes When You Connect
- See precise regional usage data using
query_energy_usage. You get electricity and gas consumption broken down by customer segment (residential, commercial) for any ZIP code you specify. This is critical for understanding localized demand spikes. - Understand infrastructure limits with
query_grid_infrastructure. The server provides capacity metrics on distribution circuits and substations, helping planners identify exactly where an upgrade or expansion is needed before a project starts. - Model future growth rates using
query_ev_adoption. You can track how many EVs are registered across different ZIP codes year over year. This directly informs planning for necessary charging infrastructure build-outs. - Measure program effectiveness by running
query_energy_efficiency. Instead of guessing, you get hard data on energy savings achieved and participation rates, letting you calculate true return on investment (ROI). - Discover the full scope of available information with
list_all_datasets. This function acts like a master index, showing every dataset PG&E tracks—from basic usage to complex solar capacity figures. - Filter data accurately using date range queries. The
query_by_date_rangetool lets you compare consumption trends year-over-year or quarter-to-quarter without manual spreadsheet manipulation.
Real-World Use Cases
Assessing new development viability
A developer needs to know if a proposed commercial building in ZIP code 94102 can be supported by the existing grid. They use list_all_datasets to find 'Grid Infrastructure,' then run query_grid_infrastructure filtered by that ZIP code and check capacity metrics. The agent returns data showing the current substation load, flagging if the site requires an immediate upgrade.
Modeling clean energy market potential
A clean tech company wants to find the best area for a solar farm. They use query_solar_generation filtered by county name and year to see current capacity vs. land availability. They then cross-reference this with query_ev_adoption data to confirm high population density, pinpointing maximum return zones.
Analyzing historical consumption changes
A researcher wants to track how residential gas usage in a specific area changed following an economic downturn. They use list_all_datasets, locate the energy usage dataset, and run query_by_date_range with start and end dates covering the relevant period for precise trend analysis.
Comparing different segments' needs
An energy consultant must compare commercial versus residential electricity load. They use list_all_datasets, then run query_energy_usage. By specifying 'Commercial' and 'Residential' as customer segments, they get side-by-side data for the same ZIP code over a set time frame.
The Tradeoffs
Querying without filtering
A user runs query_dataset with no filters. They get massive, unmanageable data dumps that are too large for the AI to parse or process effectively.
→
Always narrow your scope first. If you want usage in SF, use query_energy_usage and specify the ZIP code (e.g., 94102) and a date range. Don't leave filters open.
Guessing dataset IDs
A user tries to run query_dataset using an ID they remember but that is deprecated or incorrect, causing the query to fail with vague errors.
→
Always start by running list_all_datasets. This gives you a definitive list of current, working IDs. If unsure, use search_datasets first.
Mixing data types in one prompt
Asking the agent to 'show me EV adoption and substation capacity for ZIP code 94102.' The two tools (query_ev_adoption and query_grid_infrastructure) require different parameters, confusing the query.
→
Break it into steps. First: Use query_ev_adoption. Second: Use query_grid_infrastructure. Then, compare the results in your own prompt to synthesize the answer.
When It Fits, When It Doesn't
Use this server if your goal is quantitative analysis of regional utility metrics—specifically energy consumption (electricity/gas), grid capacity, or clean tech adoption (solar/EV). If you need that data filtered by ZIP code, region, and date range, this is the tool. Don't use it if you are looking for qualitative information, like general policy recommendations or historical text reports; those require a different type of knowledge base connection.
If your primary task is simply to find out which datasets exist but you have no idea what you need, start with list_all_datasets. If you already know the data topic (e.g., 'grid capacity') and just need to confirm the exact column names before writing code, use get_dataset_schema on the appropriate ID. Never assume a dataset contains all energy information; always check the schema first.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by PG&E Data Portals. 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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually compiling regional utility data is a nightmare of spreadsheets and portals.
The old way means logging into the PG&E portal, finding the usage dashboard, downloading the CSV for residential users in ZIP 94102. Then you repeat that process—logging out, going to the separate Solar section, and downloading a second file for capacity data. You end up with two massive spreadsheets, manually matching dates, merging by region, and cross-checking fields just to answer one question.
With this MCP server, your AI client handles all those steps in the background. Instead of clicking through three different dashboards and exporting five separate files, you just ask: 'What was peak residential usage vs. installed solar capacity in 94102 for Q3?' The agent runs `query_energy_usage` and `query_solar_generation`, stitches the results together, and gives you a single answer.
PG&E Data Portals MCP Server: Querying Energy Usage
Before this tool, analyzing energy consumption meant running separate reports for every customer segment (industrial, commercial) and then manually calculating the aggregate. If you needed to look at usage trends across multiple years, you had to download a new report every time, leading to hours of tedious data manipulation in Excel.
Now, you specify 'commercial' and a date range with `query_energy_usage`. The agent handles the filtering and aggregation instantly. You get clean, structured records that let you focus on what the numbers mean—not how long it took to pull them.
Common Questions About PG&E Data Portals MCP
How do I find all available PG&E datasets using list_all_datasets? +
Run list_all_datasets. This returns a catalog of every dataset, including energy usage, EV adoption, and grid infrastructure. It’s the best place to start when you don't know which data set you need.
What is the difference between query_dataset and get_dataset_schema? +
list_all_datasets gives you a list of available topics. get_dataset_schema drills down to show the column names, data types, and constraints for one specific dataset ID, letting you know exactly what fields you can filter on.
How do I query EV adoption rates by ZIP code? +
Use query_ev_adoption. You need to provide the 5-digit ZIP code and the specific year (YYYY format) in your prompt. This tool is designed specifically for this data type.
Can I analyze solar generation capacity trends using query_solar_generation? +
Yes, query_solar_generation handles that. You must specify the region (county name or service area) and the year to retrieve production statistics for trend analysis.
What filters can I use with query_energy_usage? +
query_energy_usage requires you to specify the ZIP code and a date range. You also select the customer segment (residential, commercial, industrial) you want to analyze.
What happens to my queries using `query_dataset` if I hit rate limits? +
You need an API key for high volume analysis. For sustained data querying, provide your PG&E Data Portals API Key during setup. This increases your allowed calls and keeps your complex analyses running without interruption.
What format must I use when calling `query_by_date_range`? +
The system requires the YYYY-MM-DD standard date format. Always pass both start and end dates using this structure to guarantee accurate filtering for any time-series comparison.
How do I narrow down my search results before running `query_dataset`? +
Use the keyword parameter when calling search_datasets. This filters the entire catalog based on your input, helping you find the exact dataset ID needed before you attempt to retrieve any data records.
What types of datasets are available? +
PG&E Data Portals offers: energy usage (electricity and gas by ZIP code), EV adoption (vehicle registrations), solar generation (capacity and production), energy efficiency programs (participation and savings), and grid infrastructure (distribution circuits, substations). Use search_datasets to discover all available datasets.
Is authentication required? +
No, the PG&E Data Portals API is publicly accessible without authentication. An API key is optional and only needed if you want higher rate limits for production use. Most queries work out of the box without any credentials.
Can I filter data by specific ZIP codes and date ranges? +
Yes! Most tools support zip_code, start_date, and end_date parameters. For example, query_energy_usage accepts ZIP code and date range to return electricity consumption for that specific area and period. Use query_by_date_range for any dataset with custom date filtering.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Vertex AI Search
Search across your enterprise data using Google's semantic search and generative AI grounding.
ANEEL Dados Abertos
Access the Brazilian National Electric Energy Agency (ANEEL) Open Data Portal to query electricity sector datasets, resources, and records.
Kraken
Get real-time cryptocurrency prices, OHLC data, order books and trades from Kraken exchange.
You might also like
Google Drive
Manage your files — search, create, share, and organize your Google Drive via AI.
Wikidata
Access the world's largest open knowledge graph—query entities via SPARQL, perform vector searches, and manage structured data directly from your AI agent.
DBpedia
Access the world's largest open knowledge graph — execute SPARQL queries, lookup entities, and monitor Wikipedia updates in real-time.