Revinho MCP server
Enables AI agents to read-only access business intelligence in a Revinho workspace, combining Google Analytics 4, Stripe, and optionally Google Search Console to answer questions about changes, performance, revenue, underperformance, and opportunities.
README
<p align="center"> <a href="https://www.revinho.com"> <img src="https://www.revinho.com/revinho-logo.svg" alt="Revinho" width="220"> </a> </p>
Revinho MCP server
Revinho gives AI agents read-only access to the business intelligence in a Revinho workspace. It combines Google Analytics 4, Stripe, and optionally Google Search Console to answer what changed, what matters, what makes money, what is underperforming, and where to focus next.
This repository is the public discovery, connection, and support home for Revinho's hosted MCP server. The production server is operated by Revinho and is not deployed from this repository.
- MCP endpoint:
https://www.revinho.com/api/mcp - Transport: Streamable HTTP
- Authentication: workspace-scoped bearer token
- Documentation: revinho.com/docs
- Registry metadata:
server.json
What it exposes
The server provides six focused tools:
| Tool | Use it for |
|---|---|
get_overview |
Headline performance, period comparisons, trends, acquisition context, freshness, and deterministic signals |
get_growth |
Channels, sources, campaigns, countries, organic queries, and acquisition segments |
get_funnels |
Saved GA4 journeys and step-by-step funnel performance |
get_pages |
Page traffic, key events, conversion, search demand, classifications, and associated impact |
get_revenue |
Stripe-sourced revenue, MRR, subscriptions, customers, refunds, plans, and currency metadata |
get_opportunities |
Ranked deterministic opportunities with evidence and attribution provenance |
Clients that support MCP prompts can also invoke investigate_business. It guides the agent through a bounded, evidence-led investigation and stops once the available facts answer the question.
Every tool is read-only, non-destructive, idempotent, and closed-world.
Connect
- Sign in to Revinho and open Setup your agent.
- Create a named workspace token. Tokens begin with
rv_live_and are shown once. - Add the hosted endpoint and token to an MCP-compatible client.
Generic configuration:
{
"mcpServers": {
"revinho": {
"type": "streamable-http",
"url": "https://www.revinho.com/api/mcp",
"headers": {
"Authorization": "Bearer rv_live_REPLACE_WITH_YOUR_TOKEN"
}
}
}
}
Client configuration formats differ. Use the client's secret or environment-variable mechanism when it supports one. Do not commit the token to a repository.
Example questions
- What changed in the business over the last 30 days?
- Which acquisition channel deserves attention first?
- Did MRR growth coincide with a change in traffic or conversion?
- Where does the purchase funnel lose the most users?
- Which pages attract demand but underperform commercially?
- What is the highest-confidence opportunity right now?
Evidence boundaries
Agents using Revinho should preserve these product rules:
- Stripe is the source of truth for revenue.
- Revenue attached to acquisition or behavior retains its
verified,modeled, orassociatedattribution label. - Non-deterministic relationships are described as coinciding or associated, never causal.
- Provider freshness fields determine data freshness. Response generation time does not.
- Missing or partial data is not silently treated as zero.
- Opportunities come from deterministic rules and stored evidence.
Token safety
Revinho API tokens are read-only, workspace-scoped, stored as cryptographic hashes, and revocable.
- Create a separate token for each agent or environment.
- Keep tokens in a secret manager or private client configuration.
- Never place a token in a URL, prompt, screenshot, issue, log, or repository.
- Revoke a token immediately if it may have been exposed.
See SECURITY.md for reporting security issues.
Support
- Product and connection help: support@revinho.com
- Security reports: security@revinho.com
- Documentation: revinho.com/docs
- Repository issues: use GitHub Issues for public, non-sensitive documentation or compatibility problems
License
The documentation and metadata in this repository are available under the MIT License. Revinho's hosted service, product code, name, and brand assets are not granted under this license.
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。