PG&E Data Portals MCP Server for Pydantic AI 10 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect PG&E Data Portals through 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 Data Portals "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in PG&E Data Portals?"
)
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 Data Portals MCP Server
Connect PG&E Data Portals to any AI agent and programmatically search, discover, and query PG&E's public energy datasets through natural conversation.
Pydantic AI validates every PG&E Data Portals tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through 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
- Dataset Search — Search the complete PG&E Data Portals catalog for energy-related datasets
- Energy Usage — Query electricity and gas consumption data by ZIP code and date range
- EV Adoption — Access electric vehicle registration and adoption trends by geographic area
- Solar Generation — Retrieve solar energy production and net energy metering (NEM) statistics
- Energy Efficiency — Analyze program participation, energy savings achieved, and cost-effectiveness
- Grid Infrastructure — Access distribution circuit, substation, and grid capacity data
- Date Range Queries — Filter any dataset by specific time periods for trend analysis
- Dataset Metadata — Get schema information and field descriptions for all datasets
The PG&E Data Portals MCP Server exposes 10 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 Data Portals to Pydantic AI via MCP
Follow these steps to integrate the PG&E Data Portals 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 10 tools from PG&E Data Portals with type-safe schemas
Why Use Pydantic AI with the PG&E Data Portals MCP Server
Pydantic AI provides unique advantages when paired with PG&E Data Portals 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 Data Portals 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 Data Portals connection logic from agent behavior for testable, maintainable code
PG&E Data Portals + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the PG&E Data Portals MCP Server delivers measurable value.
Type-safe data pipelines: query PG&E Data Portals with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple PG&E Data Portals 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 Data Portals and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock PG&E Data Portals responses and write comprehensive agent tests
PG&E Data Portals MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect PG&E Data Portals to Pydantic AI via MCP:
get_dataset_schema
Use this to understand what columns and data types are available before querying. The datasetId is obtained from search_datasets or list_all_datasets. Get the schema/metadata for a specific PG&E dataset
list_all_datasets
Each dataset includes name, description, ID, and metadata. Use this as a starting point to explore what data is available from PG&E — includes energy usage, EV adoption, solar generation, energy efficiency programs, and grid infrastructure datasets. List all available datasets in the PG&E Data Portals catalog
query_by_date_range
Specify the dataset ID and start/end dates to retrieve records within that time period. Use this for time-series analysis across any dataset type. Dataset ID from search_datasets. Dates in YYYY-MM-DD format. This is useful for year-over-year comparisons and trend analysis. Query any PG&E dataset filtered by a specific date range
query_dataset
Optional filters can be passed as key-value pairs to narrow results (e.g., zip_code, year, region). Use this to retrieve actual data records from any dataset in the PG&E Data Portals. Dataset IDs are obtained from search_datasets or list_all_datasets. Query a specific PG&E dataset with optional filters
query_energy_efficiency
), and investment amounts. Use this to analyze program effectiveness and ROI of energy efficiency initiatives. Optional programType filters by program category. Year is YYYY format. Query PG&E energy efficiency program data
query_energy_usage
Returns electricity usage aggregated by customer segment (residential, commercial, industrial, agricultural). Use this to analyze energy consumption patterns in specific geographic areas over time. ZIP code format: 5-digit (e.g., "94102"). Dates in YYYY-MM-DD format. Query PG&E energy consumption data by ZIP code and date range
query_ev_adoption
Use this to analyze EV adoption trends, identify high-adoption areas, and correlate with charging infrastructure. ZIP code is 5-digit format. Year is YYYY format (e.g., "2024"). Query electric vehicle adoption data by ZIP code and year
query_grid_infrastructure
Use this to understand grid capacity, identify areas needing upgrades, or analyze reliability metrics. Region filters by geographic area. dataType can filter by specific infrastructure type. Query PG&E grid infrastructure and distribution data
query_solar_generation
Use this to analyze solar adoption and production trends. Region can be a county name or service area identifier. Year is YYYY format. Query solar energy generation data by region and year
search_datasets
Use this to discover available datasets before querying specific data. Returns dataset names, descriptions, IDs, and metadata. Optional query parameter filters results by keyword. Search the PG&E Data Portals catalog for energy datasets
Example Prompts for PG&E Data Portals in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with PG&E Data Portals immediately.
"List all available PG&E datasets."
"Show me electricity usage for ZIP code 94102."
"Show EV adoption trends by ZIP code for 2024."
Troubleshooting PG&E Data Portals MCP Server with Pydantic AI
Common issues when connecting PG&E Data Portals to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiPG&E Data Portals + Pydantic AI FAQ
Common questions about integrating PG&E Data Portals 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 Data Portals 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 Data Portals to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.