"Adding web browsing and page reading capabilities to an agent" matching MCP servers:

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.

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.

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.

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.

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.

Enables controlling ecobee thermostats from ChatGPT by connecting a user's ecobee account through normal browser sign-in, without an ecobee developer API key. Supports listing thermostats, reading status, setting temperature or HVAC mode, and resuming schedules.

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

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

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.

An MCP server that wraps the U.S. Energy Information Administration's Open Data API, enabling assistants to fetch live energy data via natural language. It provides tools for querying series, browsing data routes, filtering facets, and running custom queries.

Connects MCP clients (e.g., Claude) to your NIBE myUplink heat-pump account for reading sensors and controlling settings via OAuth2 authentication.

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.

Exposes EnergyPlus simulation control (run, parse metrics, edit schedules) as LLM tools for autonomous building energy optimization.

Provides data-quality validation and anomaly scoring tools so an AI agent can decide whether to dispatch a field technician, while refusing to act on untrusted data.

Enables creation and validation of Canadian NECB prototype building models, application of NECB rulesets, and inspection of pinned standards/capabilities through MCP tools.

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.

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.

An MCP server that lets an MCP client control IKEA TRÅDFRI smart plugs paired to a DIRIGERA hub via its local REST API.

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.