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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.