{
  "markdown": "# Engageable\n\n**The open source analytics engine for AI agents.**\n\nOne MCP server that connects to GA4, Mixpanel, PostHog, and more. 9 tools that replace per-platform integrations. Bring your own Anthropic key.\n\n## Quickstart\n\n```bash\npip install engageable\nexport ANTHROPIC_API_KEY=sk-ant-...\nexport POSTHOG_API_KEY=phc_...\nexport POSTHOG_PROJECT_ID=12345\nengageable-mcp\n```\n\nThat's it. The MCP server is running on stdio. Connect it to Claude Desktop, Cursor, or any MCP client.\n\n## Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"engageable\": {\n      \"command\": \"engageable-mcp\",\n      \"args\": []\n    }\n  }\n}\n```\n\nRestart Claude Desktop. You'll see 9 analytics tools available.\n\n## Docker\n\n```bash\nANTHROPIC_API_KEY=sk-ant-... docker compose -f docker-compose.mcp.yml up\n```\n\nConnects via SSE at `http://localhost:8080/sse`.\n\n## Tools\n\n| Tool | What it does |\n|------|-------------|\n| `get_sources` | List connected data sources |\n| `configure_source` | Connect a new data source (saves to `~/.engageable/credentials.json`) |\n| `analyze_trends` | Time-series analysis with trend detection, change points, anomalies |\n| `compare_segments` | A/B tests, before/after, segment breakdown with statistical significance |\n| `detect_anomalies` | Find spikes, drops, and unusual patterns |\n| `analyze_retention` | Cohort retention curves (D1/D7/D30) |\n| `analyze_funnel` | Multi-step conversion funnel with drop-off rates |\n| `analyze_cohort` | Define and compare user cohorts |\n| `ask` | Natural language analytics questions (routes to other tools via LLM) |\n\n## Supported Data Sources\n\n| Source | Auth | What you need |\n|--------|------|--------------|\n| **PostHog** | API key | `POSTHOG_API_KEY` + `POSTHOG_PROJECT_ID` |\n| **Mixpanel** | Service account | `MIXPANEL_SERVICE_ACCOUNT_USERNAME` + `MIXPANEL_SERVICE_ACCOUNT_SECRET` + `MIXPANEL_PROJECT_ID` |\n| **Google Analytics 4** | Service account | `GA4_CREDENTIALS_JSON` (path or inline) + `GA4_PROPERTY_ID` |\n\nSet these as environment variables, or use the `configure_source` tool to save them interactively to `~/.engageable/credentials.json`. See [`credentials.example.json`](credentials.example.json) for the file format.\n\n## How It Works\n\nEngageable exposes analytics tools via the [Model Context Protocol (MCP)](https://modelcontextprotocol.io). Any MCP-compatible client (Claude, Cursor, VS Code, custom agents) can discover and call these tools.\n\nEach 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.\n\nResponses use CSV for tabular data (50% fewer tokens than JSON) with a 1000-cell budget to keep context windows manageable.\n\n## Architecture\n\n```\nMCP Client (Claude, Cursor, etc.)\n    │\n    ▼\n┌─────────────────────────────────────┐\n│  MCP Server (stdio or SSE)          │\n│  - Dynamic tool registration        │\n│  - Credential injection             │\n│  - CSV response formatting          │\n├─────────────────────────────────────┤\n│  Composite Skills (agent-facing)    │\n│  analyze_trends, compare_segments,  │\n│  detect_anomalies, analyze_funnel,  │\n│  analyze_retention, analyze_cohort, │\n│  ask, get_sources, configure_source │\n├─────────────────────────────────────┤\n│  Connector Skills (internal)        │  Analysis Skills (internal)\n│  ga4_query, posthog_query,          │  trend_detection, significance,\n│  mixpanel_query, + metadata/probe   │  cohort_retention, forecasting,\n│                                     │  bayesian_ab, correlation, ...\n└─────────────────────────────────────┘\n```\n\n## License\n\nMIT\n<!-- mcp-name: tech.engageable/analytics -->\n\n",
  "bytes": 3741,
  "sha": "91e31bea8b698852f31c2f2b0d5f41314ada570c5cb229bbb1272ded774def82",
  "repo_slug": "engageable-tech/engageable-oss",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_tech_engageable_analytics_bb186207/readme"
}