"Local RAG system for providing documentation to a large language model (LLM)" matching MCP servers:

MCP server that enables Google ADK agents to triage solar fault signals, retrieve Salesforce diagnostics via hosted MCP prompt templates, and create WorkOrder records when replacements are needed.

Generates deterministic solar and energy storage system preliminary proposal calculations from structured customer inputs.

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.

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.

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.

Exposes a single read-only tool that retrieves live Huawei SUN2000 inverter telemetry over local Modbus TCP, including model, firmware, active power, daily and lifetime yield, device status, and observation timing. Readings are briefly cached, with failures returned as errors rather than stale or fabricated values.

Enables LLM agents to query live data from Anker Solix solar systems (Solarbank, expansion batteries, Smartmeter) via natural language, such as current solar production or battery state of charge.

Enables searching and retrieving native EMS registers, SunSpec models and points, and closed-loop control recipes for Wattsonic MATIC hybrid inverters, validating planned Modbus writes against the documentation, and generating client code. It provides documentation only and never connects to an inverter.

MCP server for Danish electricity prices, providing current spot price, cheapest hours, and 7-day forecast for DK1 and DK2 areas.

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 local monitoring and control of a Sigenergy energy system over Modbus TCP, exposing live solar, battery, grid, load and EV charger data plus optional write tools for remote EMS modes, power and SOC limits, grid import/export caps and EV charging — no cloud account required.

A read-only BACnet/IP gateway that exposes building automation point databases to LLM agents via MCP, with Brick + Project Haystack semantic tagging at ingest time.

A Model Context Protocol server providing free financial market data across 13 categories with 83 no-key tools, enabling access to stocks, indices, options, forex, crypto, energy, prediction markets, and more.

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

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.

Enables control of Fibaro Home Center devices, scenes, variables, and system administration through natural language.

Enables AI agents to interact with a user's Fill-Rite fuel management system, with token refresh handling for continuous access.

An MCP server that enables natural language interaction with the MeteoControl VCOM API v2 for monitoring solar array installations. It allows users to retrieve real-time and historical energy data, system alerts, and detailed asset configuration metrics.

Enables MCP clients to query open data and a JSON API for the energy and CO2e cost of LLM tokens by model, GPU, and country.

Enables LLM applications to query and visualize data from Bosch/Buderus heat pumps via ems-ESP, including temperatures, statistics, and heat curves through natural language.

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

Enables Claude to validate photovoltaic system specifications and deterministically generate single-line diagrams with IEC 60617 symbols, exporting to DXF/PNG headlessly or to live AutoCAD 2027 for DWG and PDF output.

Enables turning an address or lat/lng into a transparent solar proposal by geocoding it, pulling Google Solar API building insights (panel layouts, roof segments, imagery quality), and pricing a few system sizes with your tariff, install cost, incentives, savings, payback, NPV and a verdict. Every input is labelled with its source, Google's own financial analyses are shown side by side, and no prices are invented.

Enables classifying electricity meter days as active, standby, off, or unsure from 96 fifteen-minute kWh readings plus a meter reference, with batch support for up to 31 days and model metadata. Runs fully offline as a frozen scikit-learn classifier, exposing single-day and batch classification plus model-info tools over STDIO or HTTP.

Enables users to query and download Cemig electricity bills from official sources via natural language, with read-only access and pre-paid credits across various MCP clients.

A local MCP server that enables building energy analysis through tools for anomaly detection, flexible-load schedule optimization, and battery/solar outage-autonomy simulation using reproducible synthetic data.

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

Enables users to query the UK National Grid's carbon intensity data, providing real-time and forecasted carbon emissions for electricity generation.

Enables AI agents to discover and execute solar energy domain tools such as solar cell simulation, perovskite parameter/bandgap/aging prediction, RAG knowledge retrieval, and curve/table generation through MCP.

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