shadowprice
Inject real-time leaked B2B SaaS pricing, historical discounts, and aggressive negotiation playbooks directly into AI agents.
README
<div align="center">
ShadowPrice MCP Server
Inject real B2B SaaS pricing intel directly into Claude, Cursor, and any MCP-compatible AI Agent.
</div>
What is ShadowPrice?
ShadowPrice connects your AI assistant — Claude, Cursor, or any MCP-compatible LLM — to a curated database of leaked B2B SaaS contracts, historical discount data, and negotiation playbooks.
Ask a simple question like "How much should I pay for HubSpot Enterprise?" and get back real pricing benchmarks sourced from actual contracts — not vendor list prices.
Key Capabilities
- 🔍 Contract Pricing Intelligence — Access leaked pricing from real SaaS deals.
- 📉 Historical Discount Data — See what discounts others have negotiated over time.
- 🤝 Negotiation Tactics — AI-generated strategies tailored to each vendor.
- ⚡ Zero Setup — Runs instantly via
npx -y shadowprice. No cloning, no building.
Installation
Prerequisites
- Claude Desktop, Cursor, or any MCP-compatible client installed.
- A ShadowPrice API key — get yours at shadowprice.dev.
Connect to Claude Desktop
Open your Claude Desktop config file:
| OS | Path |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%\Claude\claude_desktop_config.json |
Add the following configuration:
{
"mcpServers": {
"shadowprice": {
"command": "npx",
"args": ["-y", "shadowprice"],
"env": {
"SHADOWPRICE_API_KEY": "your_api_key_here"
}
}
}
}
[!IMPORTANT] Replace
your_api_key_herewith the API key from your shadowprice.dev dashboard.
Save the file, then quit and reopen Claude Desktop. The ShadowPrice tools will appear in the 🔨 tools menu.
Connect to Cursor IDE
- Open Cursor Settings → Features → MCP.
- Click "+ Add New MCP Server".
- Fill in the fields:
- Type:
command - Name:
ShadowPrice - Command:
npx -y shadowprice
- Type:
- Add your API key as an environment variable:
{
"SHADOWPRICE_API_KEY": "your_api_key_here"
}
[!IMPORTANT] Replace
your_api_key_herewith the API key from your shadowprice.dev dashboard.
Save the settings and restart Cursor. ShadowPrice will be available to your AI in Cursor.
Universal MCP Clients
ShadowPrice works with any MCP-compatible client — including LangChain, Dify, Flowise, and others. Configure your client to use the command transport type with the following settings:
| Field | Value |
|---|---|
| Type | command |
| Command | npx |
| Args | ["-y", "shadowprice"] |
| Env | SHADOWPRICE_API_KEY=your_api_key_here |
Most clients accept this as a JSON block:
{
"command": "npx",
"args": ["-y", "shadowprice"],
"env": {
"SHADOWPRICE_API_KEY": "your_api_key_here"
}
}
[!TIP] Pass
SHADOWPRICE_API_KEYvia your client's environment variable configuration to keep your key secure and out of version control.
Usage
Once connected, just ask your AI naturally:
| Prompt | What you get |
|---|---|
| "What's the typical pricing for HubSpot Enterprise?" | Contract benchmarks, seat pricing, tier breakdown |
| "Give me negotiation tactics for renewing our Datadog contract" | Discount ranges, leverage points, timing advice |
| "How much discount can I get on Slack Business+?" | Historical discount data from real deals |
Available Tool
get_saas_pricing_intel
Retrieve leaked B2B SaaS pricing, historical discounts, and negotiation tactics.
| Parameter | Type | Required | Description |
|---|---|---|---|
saas_name |
string | ✅ | Name of the SaaS product to look up |
License
MIT — see LICENSE for details.
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。