Connect to Google Analytics 4 (GA4) for analytics data, supporting time-series analysis, segment comparison, anomaly detection, retention, funnels, and more.
Connect to Mixpanel for product analytics, enabling trend analysis, cohort retention, funnel analysis, and natural language queries.
Connect to PostHog for product analytics, allowing trend analysis, segment comparison, anomaly detection, retention, funnels, and cohort analysis.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@tech.engageable/analytics show me last week's user signups trend"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
The open source analytics engine for AI agents.
One MCP server that connects to GA4, Mixpanel, PostHog, and more. 9 tools that replace per-platform integrations. Bring your own Anthropic key.
pip install engageable
export ANTHROPIC_API_KEY=sk-ant-...
export POSTHOG_API_KEY=phc_...
export POSTHOG_PROJECT_ID=12345
engageable-mcpThat's it. The MCP server is running on stdio. Connect it to Claude Desktop, Cursor, or any MCP client.
Related MCP server: ai-analyst
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"engageable": {
"command": "engageable-mcp",
"args": []
}
}
}Restart Claude Desktop. You'll see 9 analytics tools available.
ANTHROPIC_API_KEY=sk-ant-... docker compose -f docker-compose.mcp.yml upConnects via SSE at http://localhost:8080/sse.
Tool | What it does |
| List connected data sources |
| Connect a new data source (saves to |
| Time-series analysis with trend detection, change points, anomalies |
| A/B tests, before/after, segment breakdown with statistical significance |
| Find spikes, drops, and unusual patterns |
| Cohort retention curves (D1/D7/D30) |
| Multi-step conversion funnel with drop-off rates |
| Define and compare user cohorts |
| Natural language analytics questions (routes to other tools via LLM) |
Source | Auth | What you need |
PostHog | API key |
|
Mixpanel | Service account |
|
Google Analytics 4 | Service account |
|
Set these as environment variables, or use the configure_source tool to save them interactively to ~/.engageable/credentials.json. See credentials.example.json for the file format.
Engageable exposes analytics tools via the Model Context Protocol (MCP). Any MCP-compatible client (Claude, Cursor, VS Code, custom agents) can discover and call these tools.
Each tool is a self-contained pipeline: parse the request, fetch data from the right connector, run analysis, return results. The ask tool adds an LLM routing layer for natural language questions.
Responses use CSV for tabular data (50% fewer tokens than JSON) with a 1000-cell budget to keep context windows manageable.
MCP Client (Claude, Cursor, etc.)
│
▼
┌─────────────────────────────────────┐
│ MCP Server (stdio or SSE) │
│ - Dynamic tool registration │
│ - Credential injection │
│ - CSV response formatting │
├─────────────────────────────────────┤
│ Composite Skills (agent-facing) │
│ analyze_trends, compare_segments, │
│ detect_anomalies, analyze_funnel, │
│ analyze_retention, analyze_cohort, │
│ ask, get_sources, configure_source │
├─────────────────────────────────────┤
│ Connector Skills (internal) │ Analysis Skills (internal)
│ ga4_query, posthog_query, │ trend_detection, significance,
│ mixpanel_query, + metadata/probe │ cohort_retention, forecasting,
│ │ bayesian_ab, correlation, ...
└─────────────────────────────────────┘MIT
This server cannot be deployed
Connect Google Analytics to ChatGPT. Query GA4 data in plain English and get instant insights.
Agent-Native Amplitude/Mixpanel - connect data sources, prompt for charts
Connect your ads, shop, analytics, social, CRM and finance platforms once, then let Claude, ChatGPT, Cursor or any MCP client read, join and explain your numbers. Public statistics from the World Bank, IMF, Eurostat, OECD, WHO and SEC filings come as context, searchable and chartable from the same tools. Read-only by design, every number carries its source.
SEO & marketing toolkit for AI agents: GA4, Search Console, AdSense, GTM, PageSpeed, Trends.
