"Creating the Best General-Purpose Agent" matching MCP servers:

Enables natural-language battery-cell requirements to be parsed and routed to simulation backends, returning design forms and performance metrics while supporting calibration, thermal-runaway, COMSOL, and UI draft workflows.

MCP server that provides live facility data access and operational tools, enabling the AI agent to query sensor readings, HVAC status, energy usage, alerts, and execute confirmed maintenance actions.

Enables users to pull live heating-oil tank readings from their Smart Oil Gauge account without Home Assistant, reporting gallons remaining, percent full, usage rates, and days-until-low estimates plus usage history across daily, weekly, monthly, and yearly windows. It logs in with existing app credentials and fetches fresh data on each tool call, storing nothing on disk.

An AI-powered EV Digital Twin platform for battery health monitoring, predictive maintenance, fleet analytics, and intelligent decision support using MCP tools for SOH prediction and RUL estimation.

Enables multi-agent orchestration of distributed energy resources through MCP tools, including simulation, real-time telemetry, dispatch control, and deterministic safety gatekeeping for grid support and demand response.

AI-powered BESS quoting & energy sales intelligence for Claude and any MCP client

Enables AI agents to perform deterministic, physics-grounded grid connection screening using OpenDSS AC power flow, N-1 and SCR checks, droop compliance, and cryptographic audit receipts. It exposes typed tools and resources for screening, capacity sweeps, and auditable engineering workflows.

Enables generating yearly active and reactive power load time series for pandapower grids from German BDEW standard load profiles, with assignment of load categories, stochastic noise, scenarios, run manifests, plotting and time-series power flow. Also exposes run inspection, regeneration and verification so tool-calling LLM clients can produce and cite reproducible, checksummed results.

PyPSA MCP is a Model Context Protocol (MCP) server for creating, analyzing, and optimizing energy system models using PyPSA (Python for Power System Analysis).

Tether MOS site telemetry, mining intelligence, and energy arbitrage agent.

Enables LLM agents to inspect multi-modal IoT telemetry and query safety policies, then dispatch actuator commands through typed MCP tools that enforce deterministic safety interlocks and record a tamper-evident SHA-256 chained audit trail. This lets automated agents control building hardware without violating safety invariants, while rejecting cross-sensor false alarms and cutting redundant telemetry and token usage.

Provides tools for querying Danish day-ahead electricity prices, finding cheapest charging windows, estimating costs, and creating pending charging plans, with strict validation and human-in-the-loop approval for write operations.

Hourly electricity grid carbon intensity (gCO2eq/kWh) for 45 zones across Europe, the US and Great Britain, computed from ENTSO-E, EIA and NESO generation data. Four read-only tools; every value carries its interval timestamp and how stale it is. No API key, no account.

An unofficial read-only MCP server for Panasonic AiSEG2 home energy management controllers, enabling clients to read live power flow, per-circuit consumption, circuit names, daily totals, and historical energy/cost data from the device's local web interface.

Carbon-aware MCP scheduler that defers "do it later" / "by tomorrow" / "overnight" LLM tasks to the cleanest electricity-grid hour inside a deadline — 40-70% lower CO2 per task, 50% cheaper via Anthropic/OpenAI Batch APIs. 9 MCP tools, per-task carbon receipts to local SQLite, Apache-2.0.

Unofficial MCP server for the messdienst24.de utility portal, providing tools to retrieve heating and hot-water consumption data, download PDF reports, and compare usage trends.

Enables MCP clients to search Colombian energy and gas resolutions and legal opinions, read them in chunks or by internal search, and explore each rule's regulatory graph with validity computed from the texts themselves.

A Model Context Protocol server that connects Claude to your own Kia vehicle through the Kia Owners API, enabling vehicle status, location, odometer, EV charge state, and confirm-gated commands for doors, climate, and charging.

Enables discovery and control of Philips Hue lighting devices via a local bridge using the CLIP v2 API, without any cloud dependency.

An MCP server that exposes the U.S. Energy Information Administration (EIA) Open Data API, enabling LLMs to browse and query energy data across 17 datasets with generic, composable tools.

Generates and verifies zero-knowledge proofs locally for Energy Web Verified Compute, keeping private meter readings and blinding salts on the user's machine while enabling agents to submit verifiable proof packages.

MCP server for fetching Danish electricity spot prices (DK1/DK2) using the free elprisenligenu.dk API, providing tools to get current price, cheapest hours, and price summaries.

Provides real-time access to solar inverter data from the SolaX Cloud API, enabling queries of power output, energy yields, battery status, and grid import/export data.

DeepPVMapper is an open source, crowdsourced verified AI map of rooftop solar systems. The MCP serves as a endpoint to allow queries to the database (1.1M+ systems) in natural language. This work is based on my former PhD work.

MCP server for the German energy market master data register (MaStR), enabling querying of energy units, actors, grid connections, and more via 21 SOAP and public tools.

Enables Claude or any MCP client to read live and historical Sunsynk inverter, battery, and solar data, plus inverter settings, through the Sunsynk Connect cloud API. It is read-only and lets users ask natural-language questions about generation, consumption, charging, and configuration.

Provides real-time South African load shedding data through the EskomSePush API. Enables users to check current load shedding stages, monitor API usage, and access area-specific schedules and searches with natural language queries.

Enables AI agents to choose the lowest-carbon cloud region for a workload, with tools for ranking regions by carbon intensity and latency, and for finding optimal start times to reduce emissions.

Enables MCP clients to pull US ZIP-code-level electricity data — Scope 2 location- and market-based emission factors, Scope 1 fuel factors, hourly grid carbon intensity, plant-level emissions, retail rates, and utility tariffs — for carbon accounting, multi-site comparison, and finding the cleanest hours to run flexible loads. It requires no API key or signup and works as either a hosted remote endpoint or a local stdio process.

AI agent for Italian energy tariff comparison. Analyzes electricity and gas bills, compares 44+ offers from 13 providers, estimates savings with full ARERA regulated cost breakdown