Andru Revenue Intelligence
Buyer intelligence for technical founders who sell to enterprises — ICP scoring, persona simulation, competitive positioning, deal classification, and 14 more revenue intelligence tools. 50 free queries/month.
README
Andru Revenue Intelligence MCP Server
19 buyer intelligence tools for technical founders who sell to enterprises. ICP scoring, buyer persona simulation, competitive battlecards, MBTI-adapted messaging, deal classification, sales hiring blueprints, VC thesis matching, founder wellness, and pre-meeting briefs — built on 20 years of B2B sales pattern data.
Works immediately — no pipeline data required. Describe your product and Andru delivers pre-built buyer intelligence in seconds. Run a full pipeline for intelligence tuned to your specific market.
Installation
npm install -g mcp-server-andru-intelligence
Or run directly:
ANDRU_API_KEY=sk_live_... npx mcp-server-andru-intelligence
Configuration
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
ANDRU_API_KEY |
Yes | — | Your Andru Platform API key |
ANDRU_API_URL |
No | https://hs-andru-test.onrender.com |
API base URL |
Get your API key at platform.andru-ai.com/settings/api-keys.
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"andru-intelligence": {
"command": "npx",
"args": ["mcp-server-andru-intelligence"],
"env": {
"ANDRU_API_KEY": "sk_live_your_key_here"
}
}
}
}
Claude Code
claude mcp add andru-intelligence npx mcp-server-andru-intelligence \
--env ANDRU_API_KEY=sk_live_your_key_here
Available Tools
Qualification & Scoring
| 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 |
Buyer Intelligence
| Tool | What It Does | Latency |
|---|---|---|
get_persona_profile |
Look up who you're actually talking to — what they care about at 7 AM, why they'll say no, and exactly how to open | <50ms |
get_messaging_framework |
Get the exact words to use — MBTI-adapted so the analytical CTO and the results-driven VP Sales get different versions | <50ms |
get_competitive_positioning |
Battlecard for a specific competitor — where you win, where they'll attack, which questions to plant | <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 |
Account & Pipeline
| Tool | What It Does | Latency |
|---|---|---|
get_account_plan |
Builds the account plan you'd normally spend a weekend on — stakeholder map, MEDDICC gaps, and the unified story | <100ms |
get_icp_profile |
Returns everything Andru knows about your ideal customer — all 5 intelligence layers and the patterns that predict churn | <100ms |
get_capability_profile |
Machine-readable snapshot of what your product does and who it's for — designed for buyer-side evaluation | <50ms |
Prospecting & Meetings
| Tool | What It Does | Latency |
|---|---|---|
discover_prospects |
Finds real companies showing the same buying signals your best customers showed — searches the web live | 15-30s |
get_pre_brief |
Pre-call prep so you don't walk in cold — talk track, discovery questions, anticipated objections, and the one thing to get done | 10-20s |
CRM Syndication
| Tool | What It Does | Latency |
|---|---|---|
get_syndication_status |
Shows whether your CRM has your current intelligence or is running on stale data | <200ms |
trigger_syndication |
Pushes latest intelligence into your CRM — detects which platforms are out of date and updates only what's stale | 5-15s |
Founder Tools
| 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 |
Match your company against VC investment theses — top 5 fits with reasoning for why each thesis applies | 10-20s |
get_founder_wellness |
Burnout risk assessment with recovery recommendations — because 54% of founders are severely stressed and 81% hide it | <200ms |
simulate_buyer_persona |
Practice your pitch against a simulated CFO, CTO, or VP Sales — get the objections before the real meeting | 5-15s |
CLI
All 19 tools are also available from the command line via the companion andru-intel package:
npx andru-intel list # see all 19 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 --companyName "Acme"
Cold-Start Support
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_signals
Pass productDescription, vertical, and targetRole parameters, or let Claude infer them from your conversation. The tools use pre-built buyer intelligence (5 named buyer personas, 3 vertical segment profiles) to deliver results immediately.
Run a full Pure Signal ICP pipeline at platform.andru-ai.com for intelligence tuned to your specific product and market.
Available Resources
| URI | Description |
|---|---|
andru://icp/profile |
The complete profile of the companies you should actually be selling to — 5 intelligence layers, 7 critical questions, and churn prediction patterns |
andru://pipeline/runs |
All your pipeline runs and what each one produced — ICP layers, lead gen strategy, account plans, and deck output |
andru://accounts |
Your tracked accounts — tier, pipeline value, stakeholder count, and account plan status |
How It Works
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.
Claude Desktop/Code → MCP Server (stdio) → Andru API (HTTPS)
A2A Protocol
Andru also supports the Agent-to-Agent (A2A) protocol for direct agent-to-agent communication. The AgentCard is available at:
https://hs-andru-test.onrender.com/.well-known/agent.json
Also Available As
Chrome Extension — Sales intelligence on LinkedIn profiles, Gmail compose, and any company page. Install from Chrome Web Store.
Intelligence Briefs
Free signal reads for the questions technical founders ask at 11 PM:
- I've Done 30 Customer Interviews and Still Can't Define My ICP
- I Know My ICP But My Outreach Still Isn't Working
- My Pipeline Is Full of Companies That Like Us But Nobody's Buying Urgently
- As a Technical Founder, What Am I Getting Wrong About Sales?
- Why Does My Messaging Fall Flat Even When I'm Talking to the Right Companies?
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。