MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Measurement-based EV battery SOH estimation, validated on unseen batteries, exposed as MCP tools to an LLM agent.
★ 5 -
Felicity Solar battery MCP server + REST API — exposes live battery data to Claude Code and any MCP client
npm MIT -
energyatit-mcp-servergithub.com/kasathur/energyatit-mcp-serverupdated this year
MCP server for energy infrastructure — dispatch batteries, verify carbon, read grid meters across 8 protocols
MIT ★ 1 -
MCP server for Garmin Connect on Garmin's official Personal API: sleep, HRV, body battery, activities, and more from any MCP client
pypi MIT -
MCP server for the Aivy Developer API: let your own AI assistant (Claude, ChatGPT, Codex, Grok) read and control your solar + battery system. Sungrow, Sigenergy, FoxESS, AlphaESS, SolaX and more.
Apache-2.0 ★ 2 -
LP-based home-energy planner. Optimises a Fox ESS battery + Daikin Altherma heat pump against Octopus Agile half-hourly tariffs via a PuLP MILP solver — with closed-loop replay, scenario robustness, and an MCP tool surface for OpenClaw / Claude.
Apache-2.0 -
Node-RED controller for a Victron ESS on Cerbo GX (Venus OS): Norwegian capacity-tariff (kapasitetsledd) peak control with summer/winter tiers, DVCC battery charging, dbus-serialbattery BMS watchdog, local Tuya heat pump page, dashboards, backup/restore and an MCP server for AI agents (LAN or Tailscale).
MIT ★ 2 -
MCP server for Growatt solar inverters and batteries. Lets Claude, Cursor and other MCP clients read PV generation, load, grid import/export and battery SOC, and manage inverter settings via the Growatt ShineServer API.
MIT -
MCP Server to interface with Marstek batteries
Apache-2.0 ★ 1 -
ragkitgithub.com/cognis-digital/ragkitupdated this year
Batteries-included local RAG pipeline — ingest, index, serve
NOASSERTION -
pywrygithub.com/deeleeramone/pywryupdated this year
A lightweight and blazingly fast, cross-platform, WebView rendering engine and desktop UI toolkit for Python. Batteries included.
pypi Apache 2.0 -
Another MCP server, but with batteries included + useful integrations for personal and daily use.
MIT ★ 5 -
MCP server for the Bosch eBike Flow API with OAuth, local cache, and battery trend analysis.
pypi GPL-3.0 ★ 1 -
MCP server for Solplanet solar inverters -- read live production, battery and meter data from an AI assistant
MIT -
advanced-homeassistant-mcpgithub.com/jango-blockchained/advanced-homeassistant-mcpupdated this year
MCP server that gives AI assistants control over your Home Assistant. Including 50+ tools over 3 transports. Batteries included 🔋
Apache-2.0 ★ 58 -
Local-first MCP server for Garmin Body Battery, HRV, sleep & training data — Claude/Cursor ready
MIT ★ 13 -
Rust Garmin Connect client and MCP server giving Claude your sleep, HRV, Training Readiness, Body Battery, stress, resting HR, SpO2 and respiration data (unofficial)
Apache-2.0 -
The batteries-included, No-Code FinOps automation platform, with the AI you trust.
NOASSERTION ★ 1,082 -
Local-first Windows tray app that exposes privacy-classified ambient context — presence, foreground app, battery, power, system load — as MCP tools.
MIT ★ 3 -
China hard-tech supply-chain intel as an MCP server — pre-registered, timestamped, falsifiable signal board (semiconductors, solid-state batteries, eVTOL, innovative drugs).
MIT -
fronius-mcpgithub.com/flowiesner/fronius-mcpupdated this year
MCP server for Fronius solar inverters — ask Claude real-time questions about your PV generation, battery, and grid feed-in.
Apache-2.0 ★ 1 -
Connect your Garmin Connect health metrics (VO2Max, HRV, Sleep, Body Battery) directly to Claude Desktop using the Model Context Protocol (MCP) on macOS.
★ 1 -
Android emulator for AI agents: light (1.4 GB RAM per device), a text screen outline instead of screenshots, per-device network, battery, location, screen and Android version. CLI + MCP server.
npm MIT -
Batteries-included MCP server for email — local cache, operation queue with undo, web dashboard, OAuth2 sign-in, LLM analysis. Works with Gmail, Outlook, Yahoo, Zoho, Fastmail, ProtonMail, and any IMAP provider.
MIT -
MCP server for Garmin Connect on Garmin's official Personal API: sleep, HRV, body battery, activities, and more from Claude or any MCP client
MIT ★ 72 -
Control Eufy RoboVac vacuums with natural language through a local MCP server. Battery, cleaning, docking and manual movement over Tuya 3.3. Tested with RoboVac 35C.
-
Unofficial MCP server for the Garmin Connect Personal API: let Claude and other AI assistants read your sleep, HRV, steps, stress, Body Battery, and activities
npm Apache-2.0 -
A system health and cleanup MCP server for **Odysseus**. It checks disk, memory, processes and battery, finds large files, and can clean up old temp files.
-
A Lisp-free, Emacs-keybinding text editor for Windows built with Electron + React + TypeScript, with a built-in MCP server that lets AI agents (Claude Desktop, etc.) drive the editor. Batteries-included defaults, JSON-only config.
MIT ★ 24 -
MCP server for Garmin Connect: ask Claude about your sleep, HRV, Body Battery, training readiness, VO2max, runs and rides, analyse FIT files, and build workouts that sync to your watch. 39 tools covering 150+ Garmin Connect features.
MIT -
Self-hosted Model Context Protocol (MCP) server for Garmin Connect — let Claude and other AI assistants build native strength & pool-swim workouts and read wellness data (sleep, HRV, stress, body battery). Runs locally over stdio; single Go binary.
MIT ★ 1 -
Applications and Integrations (Book 6): EEE cores into working systems — instrumentation, embedded/IoT, robotics, industrial automation, PV, batteries, EVs, microgrids, biomedical, engineering software, digital twins, 7 projects. 40 chapters, 225 figures, 953-page PDF, MCP server.
MIT -
PhonePi MCP enables seamless integration between desktop AI tools and your smartphone, providing 23+ direct actions including SMS messaging, phone calls, contact management, snippet creation and search, clipboard sharing, notifications, battery status checks, and remote device controls.
MIT ★ 40 -
macOS DevOps toolkit for safe disk cleanup and system monitoring. Analyzes 11 domains (Docker, dev caches, browser, Xcode, logs, downloads) with risk scoring and dry-run-by-default cleaning. Includes CPU/memory/battery/network monitors and an MCP server to run everything from AI chat assistants
MIT -
Android emulator your AI agent drives on under half the RAM of Android Studio's (1.4 GB vs 3.5 GB): a text screen outline instead of screenshots, and per-device network, battery, location, screen, font and Android version. CLI + MCP server.
npm MIT -
MCP server for AI compliance audit trail and governance. 75 tools, 93 frameworks, 47 provider adapters. EU AI Act, NIST AI RMF, GDPR, CMMC, ISO 42001, OWASP Agentic Top 10, OWASP MCP Top 10, SR 11-7, NIS-2, EU Battery Reg, FERC. Adapters for OpenAI, Anthr
npm Apache-2.0 -
YouTube Autocomplete — FlashDatano update data
# YouTube Autocomplete — FlashData Get YouTube search suggestions for a query prefix, language and region. Build keyword idea sheets from actual autocomplete phrases. Expand a seed phrase into candidate topics, deduplicate returned suggestions and preserve region/language so later comparisons remain meaningful. [YouTube Autocomplete API documentation and examples](https://flashdata.dev/docs/sources/youtube_suggestions?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_suggestions-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Autocomplete listing](https://smithery.ai/servers/flashdata/youtube-autocomplete) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_suggestions`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_suggestions` without submitting a data query. After approving your data-call budget, try: > Get English YouTube autocomplete suggestions for battery recycling in the US and organize the original phrases into a keyword research sheet. This server exposes `youtube_suggestions`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call query is required. language defaults to en and region to US; region is a two-letter code. Results are phrases, not search-volume figures or video records. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_suggestions", "arguments": { "query": "battery recycling", "language": "en", "region": "US" } } ``` ## Work with the output Read the suggestion strings in results[0]. Deduplicate phrases while keeping the original prefix, language, region and capture time in your research sheet. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_suggestions", "status": "done", "results": [ [ "battery recycling at home", "battery recycling safely" ] ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling Autocomplete returns phrases, not video results or search-volume estimates. A suggestion is not evidence of demand size. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
YouTube Extended Search — FlashDatano update data
# YouTube Extended Search — FlashData Search larger YouTube video result sets, with up to 700 requested results. Map recurring channels and topics from structured video records. Group a larger topic sample by channelId or channelUrl to see which creators appear repeatedly, retaining the underlying video IDs. [YouTube Extended Search API documentation and examples](https://flashdata.dev/docs/sources/youtube_search_extended?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_search_extended-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Extended Search listing](https://smithery.ai/servers/flashdata/youtube-extended-search) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_search_extended`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_search_extended` without submitting a data query. After approving your data-call budget, try: > Search for 100 battery recycling videos, group the observed results by channel, and retain video IDs for later review. This server exposes `youtube_search_extended`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call max_results accepts 1–700, default 20. This is the extended-search product with its own higher rate, not repeated standard search or a guarantee of 700 returned records. The same supported filters are available. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_search_extended", "arguments": { "query": "battery recycling", "max_results": 100 } } ``` ## Work with the output Read results[0].results and group by channelId or channelUrl. Keep the original video IDs and count observed results per channel; retain channel labels for review. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_search_extended", "status": "done", "results": [ { "results": [ { "videoId": "dQw4w9WgXcQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 }, { "videoId": "aqz-KE-bpKQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The request limit is 700, not a promise of 700 returned videos or pagination. Extended search has its own rate, higher than standard search. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
Fsolar MCP
MIT ★ 1 -
MCP server exposing passwerk tools, resources and prompts over stdio and Streamable HTTP
npm Apache-2.0 -
Open-source hybrid renewable energy sizing for AI assistants (MCP server, CLI, Claude skill)
Apache-2.0 -
datacenter-mcp-servergithub.com/log-wade/datacenter-mcp-serverupdated this year
Mission-critical data center design & engineering MCP server. Provides cooling load calculations, power redundancy analysis, tier classification assessment, and commissioning workflow tools for AI agents.
npm MIT -
EV-recall transport compliance — ADR Class 9 (UN3480/3481/3536/3556/3557/3558), DGSA workflow, thermal-runaway routing, OEM recall protocols. For UK car transporters under ADR 2025 + ZEV Mandate. By MEOK AI Labs.
pypi MIT -
pulsar-mcp-proxygithub.com/Keithw01/pulsar-mcp-proxyupdated this year
Public MCP server for Pulsar Developments — UK distributor of Mascot power supplies. Live GBP pricing, UK stock, competitor cross-references (Mean Well, RS PRO, XP Power, Phihong, CUI, TDK-Lambda, Victron +25 more), spec search, datasheets, EOL replacements, quote requests. Streamable HTTP: https://www.pulsardevelopments.com/mcp
MIT -
Free, open-source menu bar app that keeps the app you're using fast: background apps go to efficiency cores, idle apps are frozen when memory runs low, plus per-app CPU and memory limits, a widget, and an MCP server for Claude. Apple Silicon. A rewrite of AppPolice.
GPL-2.0 ★ 1