Engageable Analytics

tech.engageablePublished by engageable.techv0.2.0Updated Oct 24, 2026

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

VerifiedSTDIODesktop onlyData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Local MCP server that connects an assistant to GA4, Mixpanel and PostHog and runs trend, funnel, cohort and anomaly analysis on that data.

What you can do
  • List and configure connected analytics data sources
  • Run time-series trend analysis with change points and anomalies
  • Compare segments and A/B tests with statistical significance
  • Detect spikes, drops and unusual patterns
  • Analyze retention cohorts, funnels and user cohorts
  • Answer natural-language analytics questions by routing to the other tools through an LLM
When to use it
Useful when you already keep product or web analytics in GA4, Mixpanel or PostHog and want an assistant to query and interpret that data without building separate integrations per platform.
Requirements
Runs locally as a Python package (pip install engageable) over stdio, or via Docker with SSE. Needs credentials per source: POSTHOG_API_KEY and POSTHOG_PROJECT_ID, MIXPANEL_SERVICE_ACCOUNT_USERNAME, MIXPANEL_SERVICE_ACCOUNT_SECRET and MIXPANEL_PROJECT_ID, or GA4_CREDENTIALS_JSON and GA4_PROPERTY_ID. The ask tool requires ANTHROPIC_API_KEY. Credentials can be set as environment variables or saved to a local credentials file.
Before you install
Requires several secrets: ANTHROPIC_API_KEY, POSTHOG_API_KEY, MIXPANEL_SERVICE_ACCOUNT_SECRET and GA4 service account credentials. The configure_source tool writes credentials to a file in the user's home directory. Analytics data is sent to the analytics vendors and, for the ask tool, to Anthropic. Read-only analysis, but it exposes production analytics data to the assistant.

Installation

In SourceWeft

  1. Open Engageable Analytics in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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

bash
pip install engageableexport ANTHROPIC_API_KEY=sk-ant-...export POSTHOG_API_KEY=phc_...export POSTHOG_PROJECT_ID=12345engageable-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:

json
{  "mcpServers": {    "engageable": {      "command": "engageable-mcp",      "args": []    }  }}

Restart Claude Desktop. You'll see 9 analytics tools available.

Docker

bash
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

Source: README.md at commit a2f0652

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.