B2B Buyer-Signal MCP
Interprets B2B buyer signals (hiring, funding, tech changes) into structured outreach implications for AI sales agents, bridging the gap between raw signal data and actionable intent.
README
B2B Buyer-Signal MCP
Intent layer for AI sales agents — structured signal interpretation, not data scraping.
Built from 10+ years of B2B enterprise sales experience.
Disclaimer. Outputs are structured signal-interpretation frameworks based on publicly-documented B2B sales practice. Not investment, financial, or legal advice. Not a substitute for human qualification. Verify any specific claim about a company, person, or event with primary sources before outreach.
Why This Exists
Every AI SDR and sales agent today has the same structural gap: they have signal data (from Apollo, Clay, Crunchbase, scrapers, paid APIs) but no consistent interpretation layer. They know a target hired a Head of Sales, but they don't know what to do with that information.
This MCP bridges that gap. Provide a signal payload — receive structured outreach implications.
It does NOT scrape data sources. Use Apify / Clay / Apollo / Crunchbase / LinkedIn ecosystem for upstream collection. This MCP is the interpretation engine.
6 Tools
| Tool | What it returns |
|---|---|
interpret_hiring_signal |
Signal strength, outreach timing, pitch angle, pitfalls, decision window for hiring events (new exec, team expansion) |
interpret_funding_signal |
Same for funding events (seed → IPO, down rounds) including budget bands and typical buyers |
interpret_tech_stack_change |
Same for tech-stack changes (added/removed competitor, warehouse adoption, compliance tooling) |
interpret_leadership_change |
Same for C-suite changes (CEO/CFO/CTO/CMO/founder departures) |
interpret_expansion_signal |
Same for market expansion (international office, vertical, product launch) |
score_buyer_intent |
Composite intent score (0-100) given multiple signals — for prioritization |
Sample Use
// AI agent observes: "Acme just hired a new Head of Sales last week + announced Series B"
// Calls:
mcp.call("interpret_hiring_signal", { signal_type: "head_of_sales" });
mcp.call("interpret_funding_signal", { funding_stage: "series_b" });
mcp.call("score_buyer_intent", { signals: ["head_of_sales", "series_b"] });
// Returns: tier, recommended action, pitch angle, decision window
Pricing
- Apify Pay-Per-Event: $0.05 per tool call
- First 10 calls free per actor
Production Roadmap
This v1.0 is the interpretation layer. Future versions:
- v1.1: Multi-signal correlation patterns (e.g., "head_of_sales + sdr_team_expansion within 30 days = pre-Series-A signal")
- v1.2: Industry-specific weightings (SaaS vs Fintech vs Healthcare have different signal half-lives)
- v1.3: Time-decay scoring (signal age affects weight)
- v2.0: Optional bring-your-own-data adapter for Clay / Apify Scrapers / Crunchbase API
Built By
Elisabeth Hitz — 10+ years of B2B enterprise sales experience across ad-tech, SaaS, media, and global hiring. Five-year stretch overshooting quota at a publicly-listed ad-tech company. Now building MCP servers for the AI agent ecosystem.
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。