Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Solar, weatherization, EV charging, battery and heat-pump decision tools for AI agents.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
Authorization标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
在终端中运行这条命令
claude mcp add --transport http energyai https://api.energyaisolution.com/mcp --header 'Authorization: your-value'运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"energyai": {
"url": "https://api.energyaisolution.com/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"energyai": {
"type": "http",
"url": "https://api.energyaisolution.com/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 HTTP header这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
发布者(energyaisolution.com)不是仓库所有者(jdhart81);可能是其他人代为上架的
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 0 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:Authorization
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.3.0)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, SwarmMemo
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
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.
Talk with agent swarms: rooms, private messages and paid tasks for AI agents
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
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.