English Français العربية

Engageable Analytics

Registre officiel Marketing et ventes

Unified analytics MCP server for GA4, Mixpanel, and PostHog.

Code source Documentation

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

PYPI package engageable
Claude Code 
claude mcp add engageable-analytics -e 'ANTHROPIC_API_KEY=<your anthropic_api_key>' -e 'POSTHOG_API_KEY=<your posthog_api_key>' -e 'POSTHOG_PROJECT_ID=<POSTHOG_PROJECT_ID>' -e 'GA4_CREDENTIALS_JSON=<your ga4_credentials_json>' -e 'GA4_PROPERTY_ID=<GA4_PROPERTY_ID>' -e 'MIXPANEL_SERVICE_ACCOUNT_USERNAME=<MIXPANEL_SERVICE_ACCOUNT_USERNAME>' -e 'MIXPANEL_SERVICE_ACCOUNT_SECRET=<your mixpanel_service_account_secret>' -e 'MIXPANEL_PROJECT_ID=<MIXPANEL_PROJECT_ID>' -- uvx engageable==0.2.0
Configuration JSON (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "engageable-analytics": {
            "command": "uvx",
            "args": [
                "engageable==0.2.0"
            ],
            "env": {
                "ANTHROPIC_API_KEY": "<your anthropic_api_key>",
                "POSTHOG_API_KEY": "<your posthog_api_key>",
                "POSTHOG_PROJECT_ID": "<POSTHOG_PROJECT_ID>",
                "GA4_CREDENTIALS_JSON": "<your ga4_credentials_json>",
                "GA4_PROPERTY_ID": "<GA4_PROPERTY_ID>",
                "MIXPANEL_SERVICE_ACCOUNT_USERNAME": "<MIXPANEL_SERVICE_ACCOUNT_USERNAME>",
                "MIXPANEL_SERVICE_ACCOUNT_SECRET": "<your mixpanel_service_account_secret>",
                "MIXPANEL_PROJECT_ID": "<MIXPANEL_PROJECT_ID>"
            }
        }
    }
}

Variables d'environnement

  • ANTHROPIC_API_KEY secret Anthropic API key (required for the 'ask' tool)
  • POSTHOG_API_KEY secret PostHog personal API key
  • POSTHOG_PROJECT_ID PostHog project ID
  • GA4_CREDENTIALS_JSON secret Google Analytics 4 service account credentials (inline JSON)
  • GA4_PROPERTY_ID Google Analytics 4 property ID
  • MIXPANEL_SERVICE_ACCOUNT_USERNAME Mixpanel service account username
  • MIXPANEL_SERVICE_ACCOUNT_SECRET secret Mixpanel service account secret
  • MIXPANEL_PROJECT_ID Mixpanel project ID

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. Engageable
  2. Quickstart
  3. Claude Desktop
  4. Docker
  5. Tools
  6. Supported Data Sources
  7. How It Works
  8. Architecture
  9. License

Engageable

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.

Quickstart

pip install engageable
export ANTHROPIC_API_KEY=sk-ant-...
export POSTHOG_API_KEY=phc_...
export POSTHOG_PROJECT_ID=12345
engageable-mcp

That's it. The MCP server is running on stdio. Connect it to Claude Desktop, Cursor, or any MCP client.

Claude Desktop

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.

Docker

ANTHROPIC_API_KEY=sk-ant-... docker compose -f docker-compose.mcp.yml up

Connects via SSE at http://localhost:8080/sse.

Tools

ToolWhat it does
get_sourcesList connected data sources
configure_sourceConnect a new data source (saves to ~/.engageable/credentials.json)
analyze_trendsTime-series analysis with trend detection, change points, anomalies
compare_segmentsA/B tests, before/after, segment breakdown with statistical significance
detect_anomaliesFind spikes, drops, and unusual patterns
analyze_retentionCohort retention curves (D1/D7/D30)
analyze_funnelMulti-step conversion funnel with drop-off rates
analyze_cohortDefine and compare user cohorts
askNatural language analytics questions (routes to other tools via LLM)

Supported Data Sources

SourceAuthWhat you need
PostHogAPI keyPOSTHOG_API_KEY + POSTHOG_PROJECT_ID
MixpanelService accountMIXPANEL_SERVICE_ACCOUNT_USERNAME + MIXPANEL_SERVICE_ACCOUNT_SECRET + MIXPANEL_PROJECT_ID
Google Analytics 4Service accountGA4_CREDENTIALS_JSON (path or inline) + GA4_PROPERTY_ID

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.

How It Works

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.

Architecture

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, ...
└─────────────────────────────────────┘

License

MIT

Questions fréquentes

Qu'est-ce que Engageable Analytics ?

Unified analytics MCP server for GA4, Mixpanel, and PostHog.

Comment installer Engageable Analytics ?

Il s'exécute sur votre machine. Dans Claude Code : claude mcp add engageable-analytics -e 'ANTHROPIC_API_KEY=<your anthropic_api_key>' -e 'POSTHOG_API_KEY=<your posthog_api_key>' -e 'POSTHOG_PROJECT_ID=<POSTHOG_PROJECT_ID>' -e 'GA4_CREDENTIALS_JSON=<your ga4_credentials_json>' -e 'GA4_PROPERTY_ID=<GA4_PROPERTY_ID>' -e 'MIXPANEL_SERVICE_ACCOUNT_USERNAME=<MIXPANEL_SERVICE_ACCOUNT_USERNAME>' -e 'MIXPANEL_SERVICE_ACCOUNT_SECRET=<your mixpanel_service_account_secret>' -e 'MIXPANEL_PROJECT_ID=<MIXPANEL_PROJECT_ID>' -- uvx engageable==0.2.0. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour Engageable Analytics ?

Oui. Il attend ANTHROPIC_API_KEY, POSTHOG_API_KEY, GA4_CREDENTIALS_JSON, MIXPANEL_SERVICE_ACCOUNT_SECRET, à renseigner dans sa configuration.

Engageable Analytics est-il open source ?

Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.

Qui maintient Engageable Analytics ?

Il est publié par engageable-tech. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.