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)
Revenue intelligence for complex B2B growth.
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。
ANDRU_API_KEY, ANDRU_API_URL, X-API-Key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。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"andru-intelligence": {
"command": "npx",
"args": [
"-y",
"mcp-server-andru-intelligence"
],
"env": {
"ANDRU_API_KEY": "your-value",
"ANDRU_API_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http andru-intelligence https://mcp.andru-ai.com/mcp --header 'X-API-Key: your-value'claude mcp add andru-intelligence --env ANDRU_API_KEY=your-value --env ANDRU_API_URL=your-value -- npx -y mcp-server-andru-intelligence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": {
"andru-intelligence": {
"url": "https://mcp.andru-ai.com/mcp",
"headers": {
"X-API-Key": "your-value"
}
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"andru-intelligence": {
"command": "npx",
"args": [
"-y",
"mcp-server-andru-intelligence"
],
"env": {
"ANDRU_API_KEY": "your-value",
"ANDRU_API_URL": "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": {
"andru-intelligence": {
"type": "http",
"url": "https://mcp.andru-ai.com/mcp",
"headers": {
"X-API-Key": "your-value"
}
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"andru-intelligence": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-server-andru-intelligence"
],
"env": {
"ANDRU_API_KEY": "your-value",
"ANDRU_API_URL": "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。
ANDRU_API_URL envX-API-Key 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。
工具名称和描述与服务器在 2026年11月7日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
preview_companyBefore any outreach: use this when the person wants to see how a company's website reads to the buyers it wants, before they have an Andru account. Returns who the company sells to, the buyers who decide, and what the site says versus what those buyers need to hear. Send the webs
signup_startGetting set up: use this when the person asks to sign up for or sign in to Andru from here. Send their email. Andru emails them a 6-digit code and an Approve button. If they read you the code, call signup_verify. If they tap Approve, call signup_status with the request_id until i
signup_verifyGetting set up: use this after signup_start when the person reads you the 6-digit code from their email. Send the email and the code. Returns an Andru API key for this agent.
signup_statusGetting set up: use this after signup_start when the person approves by tapping the button in their email instead of reading you a code. Send the request_id. Returns "waiting" (ask again after the number of seconds it gives), your API key once they approve (shown once; save it),
whoamiUse this when the person asks what this key or connection can spend, or how much is left. Returns the account, the key's name, how much it can spend today and this month without asking, the wallet balance, and free calls left today, and the portfolios this account can see, each w
quoteUse this when the person asks what a call would cost. Send the tool name and its arguments. Returns the price, whether today's free calls cover it, the wallet balance, how much this key can still spend without asking, and a quote_id that holds the price for 30 minutes. Pass quote
get_icp_fit_scoreUse this when the person asks whether one company is a good fit, before they reach out or spend more time. Scores it in seconds against the account's ICP on 5 dimensions (company profile, tech stack, pain, budget fit, buying signals) and returns an A–D tier with the reason behind
get_persona_profileUse this when the person asks what a specific buyer role cares about (a CFO, a VP of Operations) or why that person isn't responding. Returns Andru's starting picture of that buyer from the account's ICP: what they're measured on, what worries them, the concerns they need answere
get_disqualification_signalsUse this when a deal has stalled or the person wonders whether this buyer is ready for them. Checks the company against the account's ICP and the profile of companies that aren't a fit, and returns one of four fit levels with the reasons. When the answer is no, help the person te
get_messaging_frameworkUse this when the person needs to put their story in one buyer's terms: a first note to an executive about what they could change, or the same point for the CFO and the IT lead. Returns what that buyer responds to, the problem in their words, and the concerns they need answered,
get_competitive_positioningUse this when a buyer is weighing another option, or the person asks how they compare with a named alternative. Treats it as diligence for the buyer: where the alternative fits this buyer better, where the person's product does, and questions that help the buyer decide for themse
classify_opportunityUse this after a first conversation, when the person wants one read on whether this buyer is ready: fit score, how well the people involved match the buyers in their ICP, risk flags and a fit check, ending in one call: pursue, proceed with caution, deprioritize, or not a fit toda
get_account_planUse this when the person wants a plan for a specific target account. Builds a first map of the buying committee, the opportunities that fit what they sell, the likely champion, what each person needs to hear, and next steps, from sourced research, saved to their Andru account. Tr
get_evaluation_criteriaAfter discovery, checking what the buyer said they need against what the person offers: use this when the person knows what a buyer needs and wants to see how well their product matches. Pass the buyer's `buyerPainPoints` and `requiredCapabilities`. Returns 0-100 for pain coverag
get_icp_profileUse this when the person asks who their ideal customer is, who isn't a fit, or needs to explain who buys from them and why. Returns the account's ICP, built from what they sell: the enterprise buyers who decide, what each one is measured on and the concerns each needs answered, t
discover_prospectsBefore outreach, finding companies with a reason to change now: use this when the person needs new companies to sell to, for example when their pipeline is thin. Searches the web for real companies showing the problem the person's product solves right now (hiring, launches, fundi
get_pre_briefUse this when the person has a specific upcoming meeting or call and wants to be ready for it. This is the default for "prepare me for my call". Returns a short brief: what the meeting is for and what each person in the room likely thinks going in (what they want, the concerns th
batch_fit_scoreBefore outreach, choosing where to spend time: use this when the person has a list of companies to score or rank against their ICP (up to 50 at once). Returns each company's tier and score, plus totals.
get_sales_blueprintWhen the founder is ready to hand the path they've proven to a first seller: use this when the person is planning a sales hire: what role, how to pay it, how to interview for it, or how to ramp the new hire. Returns a job description, comp structure, interview questions that reve
get_thesis_matchFundraising, not selling: use this when the person is raising money and asks which investors to talk to. Finds up to 3 VC firms investing now in companies like theirs, each with a recent deal or stated focus and a link to the page it came from (a live web search, about 30 seconds
simulate_buyer_personaUse this only when the person asks to talk with, or play out the meeting with, the buyers who'll be in the room. Andru writes a brief of what each person likely thinks going in (10 briefs a day), then plays them, one or several at once, in a Deal Prep session of 25 turns, asking
get_revenue_memoryWhat Andru has learned about their buyers and deals: use this when the person asks what they decided, learned or recorded before: metrics, deal patterns, account history, decisions and habits Andru has saved. Filter by category, key pattern or memory type.
log_revenue_insightWriting down what each deal taught: use this when the person asks you to remember something about their buyers or deals: a deal decision, a reason a deal was won or lost, an ICP refinement, a metric update or a strategic pivot. Saving an existing key keeps the previous value in i
get_founder_contextThe context behind every step: use this when the person asks what Andru is, or what it knows about them or their company. Andru is the person's enterprise buyer specialist. Returns their profile, product, and memory grouped as What I Know, Patterns I've Noticed and How You Operat
get_memory_historyUse this when the person asks how one saved metric, deal stage or priority changed over time, such as "What was my MRR 3 months ago?" or "When did my biggest deal move into procurement?".
get_market_signalsUse this when the person asks what's changing in their market or their buyers' markets, or needs a reason a buyer might act now. Returns relevance-ranked signals (trends, buyer pain, moves by the alternatives buyers weigh, regulatory and tech shifts, hiring and funding), each wit
assess_company_readinessChecking whether a company's revenue engine is ready for its next stage: use this when the person wants to score one company's revenue readiness from its operating metrics (for example ARR, net revenue retention, sales cycle). Returns a Revenue Readiness Index (0-100) with stage
get_portfolio_readiness_rollupPortfolio oversight: use this when a PE or VC operator wants a scorecard across all their portfolio companies, or asks which company is most at risk. Returns each company's Revenue Readiness Index, comparable across companies, with the average, the at-risk count and customer-conc
generate_portfolio_briefPortfolio oversight: use this when a PE or VC operator wants a written brief on their portfolio companies' sales activity for a period: what Andru's work across the companies found (targets, opportunities, overlaps), each company's public news (launches, customers, partnerships,
consult_agentAny step, when no other tool fits: use this when the person asks an open question for one of Andru's domain experts. Gets a domain-scoped answer in natural language (it may call lookup tools; tools that cost money must be called directly). One turn per call; pass prior turns as `
list_assetsUse this when the person needs a deliverable, often something their champion will carry into meetings the person won't be in (a business case for the CFO, an email draft, a board deck), or asks what Andru can make. Searches Andru's catalog of 139 assets, from enterprise deals to
generate_assetBuilding the material a step needs, often what the champion carries into rooms the person won't be in: use this when the person picked an asset from Andru's catalog (find it with list_assets), e.g. 'Board Presentation', 'Buying Committee Navigation'. Built from everything Andru k
get_assetCollecting what Andru built for a step: use this when the person asks whether something Andru started is done: an asset from generate_asset, a brief from generate_portfolio_brief, or an account plan from get_account_plan. While it is building you get its progress; when it is done
cancel_jobUse this when the person wants to stop an asset that generate_asset is still building. Send the job_id. What it had written is discarded. A build that already finished stays as it is; collect it with get_asset. Briefs and account plans can't be stopped.
list_my_assetsUse this when the person asks what Andru has already built for them, or wants to open something they made earlier. Lists the assets saved to their Andru library: each one's name, when it was built, and whether it was built in part. Open one with get_asset and its asset_id.
set_product_contextUse this when the person tells you what they sell, or Andru doesn't know their product yet. Send their company website (Andru reads it and remembers the product) or a short product description, once. Andru turns it into a product description and, from that, their first ICP: who f
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
注册名称已通过 GitHub 账户 geter-andru 验证,该账户拥有此仓库
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
在 346 毫秒内响应(HTTP 200)
无需登录
已读取 36 个工具描述,未发现针对 AI 的隐藏指令
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 3 项适用的基础检查中通过了 3 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:ANDRU_API_KEY, X-API-Key
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(2.0.2)于11天前进入注册中心。
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, First Sale Scout
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.
Playbooks and a 14-day checklist for founders winning their first paying customers.
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。
An enterprise buyer specialist that already knows your buyers. Your agent builds the assets technical founders sell with, and prepares them for real buyer conversations.
Andru is an enterprise buyer specialist for complex B2B deals: it already knows your buyers and scores deals the same way every time. Give your agent 30 tools and a catalog of 139 assets, built from what Andru knows about your company and buyers. Start with:
Prepare for real conversations with buyer role-play and pre-meeting briefs (up to 10 a day). Lookups are free. Assets and role-play draw on one prepaid wallet, at the same prices as the platform: andru-ai.com/pricing.
Build any of them with generate_asset (for example generate_asset with asset: "Champion Enablement Kit"), and find the rest with list_assets.
npm install -g mcp-server-andru-intelligence
Or run directly:
npx mcp-server-andru-intelligence
Or connect to the hosted server at https://mcp.andru-ai.com/mcp.
In Cursor or VS Code, add the hosted server in one click: see Add to Cursor or VS Code.
| Variable | Required | Default | Description |
|---|---|---|---|
ANDRU_API_KEY | No | — | Your Andru API key. Without one, your agent can sign you up from the conversation. |
ANDRU_API_URL | No | https://api.andru-ai.com | API base URL. The default is Andru's production API; you don't need to change it. Your key is only sent to *.andru-ai.com or this machine; set ANDRU_ALLOW_CUSTOM_API_URL=true to use another host on purpose. |
Get your API key at platform.andru-ai.com/settings/developer.
No key yet? Start the server without one and ask your agent to sign you up. It calls signup_start with your email; you get a code and an Approve button; the session then uses the new key.
Add to your claude_desktop_config.json:
{
"mcpServers": { "andru-intelligence": { "command": "npx", "args": ["mcp-server-andru-intelligence"] } } }
Already have a key? Add "env": { "ANDRU_API_KEY": " " }. Without one, ask your agent to sign you up.
claude mcp add andru-intelligence npx mcp-server-andru-intelligence
Already have a key? Add --env ANDRU_API_KEY= .
| Tool | What It Does | Latency |
|---|---|---|
get_icp_fit_score | Tells you in seconds whether a company is worth your time — scores across 5 dimensions against who actually buys from you | <100ms |
batch_fit_score | Score up to 50 companies at once — tier and score so you can rank a list in under a second | <500ms |
classify_opportunity | Full read on a deal — fit score, persona match, risk flags, disqualification check, and a verdict: pursue, pause, or walk away | <200ms |
get_disqualification_signals | Find out if you're wasting time on a deal that won't close — three layers of signal and a clear recommendation | <200ms |
| Tool | What It Does | Latency |
|---|---|---|
get_persona_profile | Look up who you're actually talking to — what they care about at 7 AM, what they need before they say yes, and exactly how to open | <50ms |
get_messaging_framework | Your story in one buyer's terms: what they respond to, the problem in their words, and the concerns they need answered, built from your ICP | <50ms |
get_competitive_positioning | When a buyer is weighing another option: where it fits them better, where yours does, and questions that help them decide for themselves | <100ms |
get_evaluation_criteria | Scores how well you match what a buyer needs — across pain coverage, outcome clarity, capability fit, and 3 more dimensions | <100ms |
| Tool | What It Does | Latency |
|---|---|---|
get_account_plan | Builds the account plan in your Andru account and returns its link with a short summary. A plan from the last 30 days comes back at once. Returns a job_id; get_asset collects it | 1–3 min |
get_icp_profile | Your ICP, built from what you sell: the buyers who decide, what each is measured on and needs answered, the signals a company is ready to change, and who isn't a fit | <100ms |
| Tool | What It Does | Latency |
|---|---|---|
discover_prospects | Finds real companies likely to buy your product — searches the web live and links the page behind every piece of evidence | up to ~2 min |
get_pre_brief | What the meeting is for and what each person in the room likely thinks going in, built from your buying committee and labelled as assumptions to correct | 10-20s |
| Tool | What It Does | Latency |
|---|---|---|
get_sales_blueprint | First sales hire blueprint — JD, comp model, interview questions, and 90-day ramp plan for the stage you're at | 10-20s |
get_thesis_match | Up to 3 VC firms investing now in companies like yours, each with a recent deal or stated focus and a link to the page it came from | ~30s |
simulate_buyer_persona | Prepare for a meeting with the people who'll be in the room: a brief of what each person likely thinks going in (10 a day), then a Deal Prep session where Andru plays them, one or several at once | 5-15s |
| Tool | What It Does | Latency |
|---|---|---|
get_revenue_memory | Query what Andru has learned about your business over time: metrics, deal patterns, account history, decisions | varies |
log_revenue_insight | Save an insight, decision, metric or pattern to Andru's memory; earlier values are versioned automatically | varies |
get_founder_context | Everything Andru knows about you, organised by memory type | varies |
get_memory_history | How a metric, deal stage or priority has changed over time ("What was my MRR 3 months ago?") | varies |
| Tool | What It Does | Latency |
|---|---|---|
get_market_signals | What's moving in your market now: ranked signals, each with its buyer impact and a recommended action | varies |
assess_company_readiness | Scores a company's Revenue Readiness Index (0–100) from its operating metrics, with its #1 growth constraint | varies |
get_portfolio_readiness_rollup | A board-ready scorecard of every portfolio company by Revenue Readiness Index, with aggregates | varies |
generate_portfolio_brief | A brief on your portfolio's sales activity for a period, with sources (not a financial or performance report) | a few min |
| Tool | What It Does | Latency |
|---|---|---|
consult_agent | Ask one of Andru's domain expert agents in natural language and get a domain-scoped answer | varies |
| Tool | What It Does |
|---|---|
list_assets | Search Andru's catalog of 139 assets, from enterprise deals to hiring, fundraising and buying: what each is, its business outcome, and whether it can be generated today |
generate_asset | Generate any catalog asset from everything Andru knows about your company; saved to your Andru library |
get_asset | Collect a generated asset or portfolio brief as markdown, or an account plan's link and summary |
cancel_job | Stop an asset that generate_asset is still building; what it had written is discarded. A build that already finished stays as it is |
list_my_assets | List the assets saved to your Andru library: each one's name, when it was built, and whether it was built in part. Open one with get_asset and its asset_id |
| Tool | What It Does |
|---|---|
set_product_context | Tell Andru what you sell, once: your company website (Andru reads it) or a short description. Every later call uses it |
Andru charges from a prepaid wallet, at the same prices as the platform: andru-ai.com/pricing. Answers from your own data are free, and a call that only asks you for more information is never charged. Your wallet balance is at platform.andru-ai.com/settings/billing.
These tools are also available from the command line via the companion andru-intel package:
npx andru-intel assets board # search the asset catalog (free)
npx andru-intel generate "Board Presentation" --out board-deck.md # build it, save as markdown npx andru-intel list # see all tools npx andru-intel score "AI code review" # instant ICP (works offline) npx andru-intel persona CFO # buyer persona deep dive npx andru-intel blueprint --stage "Series A" --arr "$2M" npx andru-intel thesis "AI sales platform" --stage "Seed" npx andru-intel roleplay CTO npx andru-intel wellness npx andru-intel run get_competitive_positioning --competitorName " "
7 tools work without any pipeline data — just describe your product:
get_icp_fit_score, get_persona_profile, get_messaging_framework, get_competitive_positioning, get_evaluation_criteria, classify_opportunity, get_disqualification_signalsAndru only needs to know what you sell once:
set_product_context with your website (or a description) once.You can still pass productDescription, vertical, and targetRole on any call; what you send first is remembered. The tools use pre-built stakeholder understanding (5 pre-built buyer personas, 3 vertical segment profiles) to deliver results immediately.
Run a full ICP pipeline at platform.andru-ai.com for understanding tuned to your specific product and market.
| URI | Description |
|---|---|
andru://accounts | Your tracked accounts — tier, pipeline value, stakeholder count, and account plan status |
This MCP server is a thin proxy that authenticates with your Andru API key and forwards tool/resource requests to the Andru backend. All intelligence generation, ICP scoring, and data access happens server-side — the MCP server itself is stateless.
When your AI app connects, the server tells Andru the app's name and version. Each tool call is recorded by tool name, outcome and cost; what you typed isn't part of that record.
Claude Desktop/Code → MCP Server (stdio) → Andru API (HTTPS)
Andru also supports the Agent-to-Agent (A2A) protocol for direct agent-to-agent communication. The AgentCard is available at:
https://api.andru-ai.com/.well-known/agent-card.json
Free signal reads for the questions technical founders ask at 11 PM:
只显示了开头部分;其余内容请在仓库中阅读