UtilityAPI MCP Server for Pydantic AI 12 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect UtilityAPI 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 UtilityAPI "
"(12 tools)."
),
)
result = await agent.run(
"What tools are available in UtilityAPI?"
)
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 UtilityAPI MCP Server
Connect UtilityAPI to any AI agent and access utility billing history, granular usage intervals, and meter data from over 100 US utility companies — including PG&E, Southern California Edison, Con Edison, National Grid, and more — through a single unified API.
Pydantic AI validates every UtilityAPI tool response against typed schemas, catching data inconsistencies at build time. Connect 12 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
- Supported Utilities — List all 100+ utility companies available through the platform with their codes and data types
- Customer Authorizations — Create and manage authorization forms for customers to securely share their utility data
- Meter Management — List all authorized utility meters (service points) with addresses, fuel types, and collection status
- Billing History — Retrieve complete billing history with costs, usage amounts (kWh/therms), and billing periods
- Usage Intervals — Access granular smart meter interval data (15-min or hourly readings) for detailed energy analysis
- Historical Collection — Activate backfilling of historical utility data for newly authorized meters
- Combined Meter Data — Get both bills and intervals in a single call for comprehensive energy analysis
- Event Monitoring — Monitor webhook events for authorization flows, data collection status, and errors
- Demo Testing — Test authorization forms with simulated residential and commercial scenarios before production
- Billing Summaries — Track API usage costs and billing periods for your UtilityAPI account
The UtilityAPI MCP Server exposes 12 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 UtilityAPI to Pydantic AI via MCP
Follow these steps to integrate the UtilityAPI 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 12 tools from UtilityAPI with type-safe schemas
Why Use Pydantic AI with the UtilityAPI MCP Server
Pydantic AI provides unique advantages when paired with UtilityAPI 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 UtilityAPI integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your UtilityAPI connection logic from agent behavior for testable, maintainable code
UtilityAPI + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the UtilityAPI MCP Server delivers measurable value.
Type-safe data pipelines: query UtilityAPI with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple UtilityAPI tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query UtilityAPI and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock UtilityAPI responses and write comprehensive agent tests
UtilityAPI MCP Tools for Pydantic AI (12)
These 12 tools become available when you connect UtilityAPI to Pydantic AI via MCP:
activate_historical_collection
Send an array of meter_uids (from list_meters) to begin backfilling historical data. Once activated, the system will start collecting all available historical data for those meters. Use this after a new customer authorization to ensure you get their complete usage history, not just future data. Data collection may take time depending on the utility and data availability. Activate historical data collection for specific utility meters
create_auth_form
Returns a form_uid that can be used to redirect customers to the authorization flow. The utilityCode parameter must be a valid utility code (from list_utilities). Optional scenario parameter controls the test mode: "residential" (home customer), "commercial" (business customer), or other utility-specific scenarios. Use this to set up new data sharing agreements with utility customers. Create a new authorization form for customers to share their utility data
get_billing_summaries
Includes billing periods, costs, and meter counts for your UtilityAPI subscription. Optional meterId parameter retrieves summary for a specific meter. Use this to track API usage costs and understand billing periods for your UtilityAPI account. Get billing account summaries for UtilityAPI accounting
get_bills
Returns utility bills with: start/end dates, total cost (in dollars), energy usage (kWh for electric, therms for gas), utility name, and meter association. The meters parameter is required — provide a single meter UID or comma-separated multiple UIDs. Use this to analyze customer spending on utilities, identify high-cost periods, or provide billing insights. Bills are only available for meters that have been authorized and are actively collecting data. Get utility billing history for authorized meters
get_events
Events include: new authorization created, meter data available, collection completed, errors, etc. Use this to monitor the status of data collection workflows, debug authorization issues, or build real-time notifications for when customer data becomes available. Get webhook events from UtilityAPI (authorizations, data collection status)
get_form_templates
Templates define what information is collected during the customer authorization process. Use this to understand available form configurations before creating custom authorization forms. Each template has a unique ID used when creating new forms. Get authorization form templates used for customer data sharing
get_intervals
This is granular consumption data showing energy usage over time intervals (typically 15-minute or hourly readings from smart meters). Each interval includes: start/end timestamp, usage value (kWh or therms), and cost information. The meters parameter is required — provide meter UID(s). Use this for detailed energy analysis, identifying peak usage patterns, demand response analysis, or building energy models. This is more granular than bills — ideal for time-series analysis. Get detailed usage interval data (hourly/15-min) for authorized meters
get_meter_data
This is a convenience tool that combines results from get_bills and get_intervals for one meter. Returns: complete bill history (dates, costs, usage) plus granular interval data (time-series readings). Use this when you need a complete picture of a customer's utility data — both the financial (billing) and technical (usage patterns) aspects — for comprehensive energy analysis. The meterUid must be a valid meter UID from list_meters. Get combined billing and interval data for a specific meter in one call
list_authorizations
Each authorization represents a customer who has granted access to their utility data. Optional referrals parameter filters by a specific referral code (from test submissions). Set includeMeters=true to also return associated meter data with each authorization. Use this to track which customers have authorized data access and get their referral codes for meter queries. List all customer data sharing authorizations
list_meters
Each meter represents a specific utility service connection (electricity or gas) at a customer location. Meter data includes: utility name, service address, fuel type (electric/gas), collection status, and the unique meter_uid used for fetching bills and intervals. Optional authorizationId filters meters to a specific customer authorization. Use the meter_uid with get_bills and get_intervals to retrieve usage data. List all authorized utility meters (service points)
list_utilities
Each utility includes its name, utility code (used for form submissions), and supported data types. Use this to find the correct utility code when creating authorization forms or querying utility-specific data. Common utilities include: PG&E (Pacific Gas & Electric), SCE (Southern California Edison), Con Edison, National Grid, and many others across the US. List all supported utility companies available through UtilityAPI
test_form_submission
Returns a referral_code that can be used to retrieve the test authorization and associated meter data. Use this during development and testing to verify form configurations work correctly before deploying to production. The formId is the uid returned by create_auth_form. The referral_code returned can be used with list_authorizations to retrieve test data. Test an authorization form to simulate customer authorization and get a referral code
Example Prompts for UtilityAPI in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with UtilityAPI immediately.
"List all supported utility companies."
"Get the billing history for meter 44445555."
"Show me the usage intervals for my authorized PG&E meters."
Troubleshooting UtilityAPI MCP Server with Pydantic AI
Common issues when connecting UtilityAPI to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiUtilityAPI + Pydantic AI FAQ
Common questions about integrating UtilityAPI 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 UtilityAPI 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 UtilityAPI to Pydantic AI
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.