Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Descripción del creador (original en inglés)
Solar, weatherization, EV charging, battery and heat-pump decision tools for AI agents.
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
AuthorizationLos valores marcados como secretos son llaves de tu cuenta. Nunca los compartas ni los pegues en un chat.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Esta dirección necesita una clave en un header de la solicitud, y el menú para agregar conectores no puede ponerla. Usa Claude Code, Cursor o VS Code.
Ejecuta esto en tu terminal
claude mcp add --transport http energyai https://api.energyaisolution.com/mcp --header 'Authorization: your-value'Completa los valores vacíos antes de ejecutarlo.
Pégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"energyai": {
"url": "https://api.energyaisolution.com/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"energyai": {
"type": "http",
"url": "https://api.energyaisolution.com/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Esta dirección necesita una clave en un header de la solicitud, y el menú para agregar conectores no puede ponerla. Usa Claude Code, Cursor o VS Code.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Authorization secreto HTTP headerEsta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Todavía no hemos leído la lista de herramientas de este servidor; revisamos los endpoints por turnos.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 7 nov 2026
Quien lo publicó (energyaisolution.com) no es el dueño del repo (jdhart81); puede que otra persona lo haya listado
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Aún sin revisar; revisamos los endpoints por turnos
Aún sin revisar; revisamos los endpoints por turnos
Aún sin revisar; leemos la lista de herramientas cuando revisamos el endpoint
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 0 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
Debes completar: Authorization
Se ejecuta en la nube del creador. Te conectas por internet sin instalar nada, pero lo que envías pasa por los servidores del creador.
El repo de GitHub cambió por última vez –, y la última versión (1.3.0) llegó al registro hace 2 meses.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. Se conecta por URL, así que también funcionan las apps que aceptan servidores MCP remotos, como ChatGPT en modo desarrollador.
En la misma categoría: Spec Driven Development, Remote Desktop Commander, Systemdox
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Your architecture in your agents' context: checks, specs, ADRs and docs over MCP, at write time.
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
Solar estimates, incentive sources, provisional Energy Node Scores, cited guides, contractor discovery and consented installer routing — through MCP and REST. By Viridis LLC.
The public catalog supports solar, weatherization, EV charging, home batteries and heat-pump planning. Twelve tools need no key to start. Estimates and scores use supplied facts and stated assumptions; they do not establish site suitability, incentive eligibility, installation approval or verified savings.
curl -X POST https://api.energyaisolution.com/api/v1/agent/check_incentives \
-H 'content-type: application/json' -d '{"args":{"zipCode":"59715"}}'
This requests incentive source guidance for a US ZIP. For a production estimate, use estimate_production with {"zipCode":"59715","systemKw":6}. For a provisional score, use get_node_score with {"zipCode":"59715","serviceType":"solar","monthlyBillRange":"150_250"}. These informational tools accept omitted inputs with documented assumptions or broader guidance; inspect the live schema for the job you need.
https://api.energyaisolution.com/mcphttps://api.energyaisolution.com/mcp/solarPOST https://api.energyaisolution.com/api/v1/agent/{tool}llms.txt is the short index; AGENTS.md holds the consent, key and pricing rules agents must follow.com.energyaisolution/energyai · com.energyaisolution/solar-home-incentivesThe five informational tools share 20 anonymous calls per caller per 24 hours. A free key includes 100 informational calls per rolling 30 days. Sustained informational use requires an active Builder subscription; prepaid credit funds priced commercial tools.
| Informational tool | What you get |
|---|---|
check_incentives | Source-linked incentive guidance by country and postal code; eligibility remains unverified. |
estimate_production | A modeled annual solar production range with assumptions. |
get_node_score | A provisional seven-axis score and next action from supplied property facts. |
list_guides | US home-energy guides by state and topic, with sources and canonical links. |
get_guide | One source-cited guide by returned slug. |
These seven tools remain free without a key:
| Tool | What you get |
|---|---|
get_quote_link | Optional household assessment and human-review handoffs; no project submission or payment. |
get_power_passport_link | A website handoff for a candidate site and workload; scope review precedes payment. |
get_power_service_quote | A signed, time-limited quote for a Power Screen; creating the quote does not spend funds. |
route_lead | A consented homeowner project submitted to the guarded installer-matching workflow. Unmatched projects may remain recorded. |
create_builder_key | A production key after the human operator has authorized the Terms and Privacy Policy. |
get_builder_upgrade_link | A human activation, Builder or prepaid handoff; the caller cannot accept terms or pay for the human. |
find_local_installers | Public-reputation contractor options. Public listings do not imply EnergyAI vetting, endorsement or partnership. |
Hourly safety limits also apply: 120 calls per caller, with route_lead limited to 10 per hour. Read each tool's schema and consent requirements before submitting information or requesting a key.
{ "mcpServers": {
"energyai": { "type": "http", "url": "https://api.energyaisolution.com/mcp" } }}
claude mcp add --transport http energyai https://api.energyaisolution.com/mcp
For OpenAI function calling or other tool clients, fetch the function specification. See examples/ for Python and shell clients.
After authorized key activation, call review_installer_quote on the full MCP endpoint with postalCode and redacted quoteText (at most 6,000 characters), or an assessmentId belonging to the Builder account. Use serviceType for solar, battery, EV charging, efficiency or heat pumps. No prior assessment setup is required.
The public price is $0.10 per call, covered by a new key's three eligible commercial trials. The result provides source-matched terms, practical installer questions and explicit unknowns. It is automated decision support; human review, price fairness, incentive eligibility and useful household delivery are not established by a successful tool response.
bootstrap_energy_project also costs $0.10 and creates persisted project context, a provisional score, an input-coverage map and a reusable assessmentId when a quote is not yet available. Use free check_incentives for general guidance; the paid get_energy_incentives requires a completed assessment.
New keys include three trial calls for eligible tools priced at $0.25 or less, after operator-authorized Terms acceptance. Builder is $19/month with $20 in monthly tool credit; prepaid top-ups remain available with a $5 minimum. Consult live pricing and plan details before a billed call, and use an operator-approved spending ceiling. Key creation, terms acceptance and subscription activation are separate steps.
If the operator has not authorized the Terms and Privacy Policy, present the human activation link from get_builder_upgrade_link. Store a returned key securely; never print it in a user-visible reply. record_quote_review_outcome is a free, keyed tool for recording actual operator-confirmed usefulness and household delivery status; never infer that feedback from technical success.
consentTextForRouting from check_incentives.route_lead with the required project and contact details, consentText and consentTimestamp. Alternate consent language requires an explicit consentVersion.leadId and actual routing status. Prefer get_quote_link when consent is not already available.The current public quote handoff describes an authenticated referral incentive as 20% non-cash EnergyAI tool credit after verified purchase. Disclose that interest, preserve the customer price and independent review, and consult the current terms. This is not a cash bounty or evidence that a purchase occurred.
The physics ledger presents platform-reported research context and metrics. Model-based estimates, software checks and reported metrics do not by themselves establish measured physical energy, empirical performance or a certified thermodynamic bound.
Both manifests in manifests/ match the official registry's active latest v1.3.0 entries observed on October 7, 2026. The live catalog also reports v1.3.0. Registry presence and endpoint responses are availability evidence; they do not establish adoption, paid delivery, repeat use or revenue.
This repository contains documentation and client examples. The service is hosted separately; merging these files does not publish a registry version, deploy the service or activate a customer account.
Documentation and examples: MIT. The hosted service is © Viridis LLC.