PG&E Public Datasets MCP Server for Pydantic AI 8 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect PG&E Public Datasets through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to PG&E Public Datasets "
"(8 tools)."
),
)
result = await agent.run(
"What tools are available in PG&E Public Datasets?"
)
print(result.data)
asyncio.run(main())
* 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 PG&E Public Datasets MCP Server
Access PG&E Public Datasets directly from any AI agent and explore energy consumption, billing trends, efficiency savings, and regional comparisons without any authentication.
Pydantic AI validates every PG&E Public Datasets tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Monthly Usage — Get monthly electricity and gas consumption by ZIP code and customer segment
- Customer Segments — View energy usage breakdown across Residential, Commercial, Industrial, and Agricultural sectors
- Yearly Trends — Analyze year-over-year energy consumption trends
- Electricity by ZIP — Access ZIP code-level electricity consumption data
- Gas by ZIP — Access ZIP code-level natural gas consumption data
- Billing Data — Retrieve average bills and cost metrics by region
- Savings Data — Analyze energy efficiency program savings and cost-effectiveness
- Regional Comparisons — Compare energy usage across multiple ZIP codes side-by-side
The PG&E Public Datasets MCP Server exposes 8 tools through the Vinkius. Connect it to Pydantic AI 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 PG&E Public Datasets to Pydantic AI via MCP
Follow these steps to integrate the PG&E Public Datasets MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 8 tools from PG&E Public Datasets with type-safe schemas
Why Use Pydantic AI with the PG&E Public Datasets MCP Server
Pydantic AI provides unique advantages when paired with PG&E Public Datasets through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your PG&E Public Datasets integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your PG&E Public Datasets connection logic from agent behavior for testable, maintainable code
PG&E Public Datasets + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the PG&E Public Datasets MCP Server delivers measurable value.
Type-safe data pipelines: query PG&E Public Datasets with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple PG&E Public Datasets tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query PG&E Public Datasets and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock PG&E Public Datasets responses and write comprehensive agent tests
PG&E Public Datasets MCP Tools for Pydantic AI (8)
These 8 tools become available when you connect PG&E Public Datasets to Pydantic AI via MCP:
compare_regions
Returns side-by-side usage figures (kWh and therms), customer counts, and average bills for each region. Use this to identify regional differences in energy consumption, support geographic targeting for efficiency programs, or compare urban vs. rural usage patterns. ZIP codes are comma-separated (e.g., "94102,94103,94104"). Optional dataType and year filters. Compare energy usage data between multiple ZIP codes/regions
get_billing_data
Data is available by ZIP code and customer segment. Use this to analyze energy affordability, compare costs across regions, or identify rate impact on customers. Optional zipCode and year filters. Get billing data and average costs from PG&E public datasets
get_electricity_by_zip
Returns monthly or annual usage figures broken down by geographic area. Use this to compare electricity usage across neighborhoods, identify high-consumption areas, or support energy efficiency targeting. Optional year filter. Get electricity consumption data for specific ZIP codes in PG&E service area
get_gas_by_zip
Returns monthly or annual gas usage figures by geographic area. Use this to analyze heating demand patterns, compare gas usage across regions, or identify electrification opportunities. Optional year filter. Get natural gas consumption data for specific ZIP codes in PG&E service area
get_monthly_usage
Data is organized by ZIP code, month, year, and customer segment (Residential, Commercial, Industrial, Agricultural). Returns kWh for electric and therms for gas. Use this to analyze consumption patterns over time. Optional filters: dataType ("electric" or "gas"), customerType, zipCode (5-digit), and year (YYYY). Get monthly energy consumption data by ZIP code and customer segment from PG&E public datasets
get_savings_data
Includes program participation counts, kWh/therms saved, program costs, and cost-effectiveness metrics by program type. Use this to evaluate program ROI, compare effectiveness across initiatives, or identify high-impact efficiency strategies. Optional programType and year filters. Get energy efficiency program savings data from PG&E
get_usage_by_customer_type
Shows total consumption for Residential, Commercial, Industrial, and Agricultural sectors. Use this to understand the energy consumption distribution across different customer categories. Optional dataType ("electric"/"gas") and year filters. Get energy usage broken down by customer segment (residential, commercial, industrial, agricultural)
get_yearly_trends
Shows how electricity and gas usage has changed over multiple years. Use this to identify long-term patterns, growth/decline in energy demand, and seasonal variations. Optional dataType filter ("electric" or "gas"). Get yearly energy consumption trends from PG&E public data
Example Prompts for PG&E Public Datasets in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with PG&E Public Datasets immediately.
"Show monthly electricity usage by customer type."
"Compare ZIP codes 94102, 94301, and 95054."
"Show yearly energy consumption trends."
Troubleshooting PG&E Public Datasets MCP Server with Pydantic AI
Common issues when connecting PG&E Public Datasets to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiPG&E Public Datasets + Pydantic AI FAQ
Common questions about integrating PG&E Public Datasets MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect PG&E Public Datasets with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect PG&E Public Datasets to Pydantic AI
Get your token, paste the configuration, and start using 8 tools in under 2 minutes. No API key management needed.