"Improving the Thinking Capabilities of My Gemini AI" matching MCP servers:

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.

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 calculation of the most economical fuel (gasoline, ethanol, or natural gas) based on prices and vehicle consumption, following the 70% rule for ethanol and 60% for GNV.

An OpenStreetMap MCP server providing geocoding, routing, points of interest, map tiles, public transport, and energy infrastructure tools to enhance LLM location-based capabilities.

MCP server for querying and simulating the dispatch plan of a solar PV + battery system in the Chilean electricity market, using deterministic optimization and optional DRL.

An MCP server that enables AI assistants to look up solar permitting authorities, estimate solar production via PVWatts, and retrieve irradiance data. It streamlines the creation of solar-aware workflows by integrating industry-standard APIs like NREL.

Personal MCP hub exposing Tesla, ChargePoint, and Outlook mail as tools, enabling natural-language queries through Gemini.

Enables consultation of Enel RJ electricity bills through official sources, featuring download and OCR capabilities. It is a read-only MCP server that works with any MCP-compatible client, using prepaid credits.

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.

Enables users to consult and download second copies (2ª via) of Comgás gas bills from the official source via a read-only tool, with prepaid per-query credit.

Enables LLMs to verify the novelty and validity of invented battery materials, with support for searching and validating against a materials database.

WattScope helps teams see the carbon cost of the AI they are already using. Ask Claude to record a piece of work and it attributes the estimated footprint to your organization and to a project, then reports it back — per session, per project, or organization-wide. Every figure is an estimate, and carries the strength of the evidence behind it.

Provides offline access to the Brick Schema ontology, enabling validation and search of building metadata classes through MCP tools.

MCP server for the Arcadia Arc utility data API, enabling retrieval of bill data, interval meter readings, and carbon calculations.

Enables utility operators to forecast transformer oil temperature, assess synthetic outage risk, rank impacted assets, and generate maintenance plans through IBM Bob MCP tools.

Exposes EnergyPlus building simulation tools as MCP endpoints, enabling LLMs to run closed-loop energy optimization while maintaining occupant comfort.

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.

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.

Read-only MCP server for Home Assistant that computes statistical summaries, trends, and session detection from recorded sensor history, returning compact tables instead of raw data so small local models can answer questions about energy usage, climate, and appliance activity without token-heavy arithmetic.