"Startups in AI, Large Language Models, and AI Agents" 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.

Autonomous, carbon-aware building management system that pairs EnergyPlus digital twins with LLMs via the Model Context Protocol (MCP) for dynamic HVAC optimization and grid carbon reduction.

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.

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.

The PGIQ Rating as agent tools: where to site or schedule a large electricity load across 67 global power markets. Wraps a read-only REST API returning reasoned, cited ratings across access, availability, cost, momentum, and carbon, plus live grid snapshots and cheapest-window scheduling.

Enables AI agents and assistants to query Polish electricity market data from the SENS Energy Data API by discovering operators and tariffs, fetching composite prices, and inspecting tariff components through natural language.

MCP server for Kardashev Labs US grid data, giving agents live LMP, carbon intensity, load, curtailment, interconnection queues, ERCOT large loads, and the public RT-DA spread forecast track record. Requires no API key.

Enables AI assistants to create, edit, and simulate EnergyPlus building energy models via natural language. Supports schema exploration, model editing, simulation execution, and documentation search.

MCP server for OpenHAB v5+ that exposes the entire REST API as tools for AI models, enabling complete control over items, things, rules, persistence, and semantic model.

MCP server providing tools for AI-agents to interact with Enapter EMS.

Enables querying of real-time and forecast UK carbon intensity data from National Grid ESO, allowing AI agents to retrieve carbon emissions by region and time.

Enables AI agents to query UK energy tariffs and products via the Octopus Energy public API.

Enables AI agents to understand, query, and manipulate Honeybee building energy models through natural language via the Model Context Protocol.

Enables Claude AI to control and manage Homey Pro smart home devices, flows, and analytics through natural language.

A physics engine for liquid-cooled GPU systems, exposed as an AI-callable MCP server. Enables thermal analysis, coolant comparison, flow optimization, and rack-level sizing via natural language queries.

MCP server for the Carbon Interface API (v1), enabling AI agents to estimate carbon emissions through natural language queries via Pipeworx gateway.

Enables AI agents to interact with the OSDU® data platform through Model Context Protocol, providing tools for search, storage, schema management, and dataset operations.

MCP server that gives AI agents real-time German electricity price forecasts.