</>MCP Agents Market
MCP Server

retentioneering-tools

by retentioneering918PythonUpdated 2026-09-11

Python toolkit, MCP server, and agent skills for reproducible, auditable clickstream and event log analytics. Helps AI agents, data scientists and analysts build, validate, and cross-check product analytics, quantitative UX, customer journeys, graph-based user flows, behavioral segmentation, A/B tes

Claude DesktopJupyterGoogle ColabVS CodeCursorClaude Code

Retentioneering-tools is an open-source Python toolkit and MCP server for reproducible product analytics on clickstream and event log data. It enables AI agents and data scientists to analyze user journeys, behavioral segments, A/B tests, and conversion paths using tested analytical primitives instead of one-off scripts. The MCP server exposes eventstream objects to Claude and compatible clients, letting agents explore user flows, build validated analyses, and export interactive HTML reports where every metric links to its source computation.

Key Features

MCP server integration that exposes eventstream analytics to Claude and other MCP clients for agent-driven analysis
Interactive widgets including Transition Graph, Step Matrix, Step Sankey, Funnel, Segment Overview, and Cluster Analysis
DuckDB-backed Eventstream engine for fast analysis of clickstream, product events, and timestamped behavioral data
Diff mode in all widgets to visually compare two cohorts or experiment groups side-by-side
Chainable data processors for filtering, sessionization, event collapsing, synthetic event injection, and behavioral sampling
Multi-resolution analysis from individual events to sessions, episodes, lifecycle stages, and long-term customer journeys
Path metrics registry for behavioral clustering, segment comparison, and custom ML feature engineering
Agent skills and reusable analytical primitives designed to reduce token usage and minimize analytical errors

Use Cases

  • 01Identifying where users get stuck or drop off in product flows and conversion funnels
  • 02Discovering alternative routes to conversion, behavioral loops, dead ends, and hidden user segments
  • 03Comparing user journeys and flow patterns between A/B test groups or customer cohorts
  • 04Analyzing quantitative UX and customer journey data across sessions and long-term lifecycle stages
  • 05Enabling AI agents to cross-check product analytics results through reproducible, auditable computations
  • 06Building shareable HTML reports of behavioral insights that link every metric to its source analysis

Related MCP Servers

View more

markitdown

Python tool for converting files and office documents to Markdown.

MCP Server187.8k

firecrawl

The context API to search, scrape, and interact with the web at scale. 🔥

MCP Server187.2k

prompts.chat

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

MCP Server171.7k

langflow

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

MCP Server155.4k

retentioneering-tools — FAQ

What is the Retentioneering-tools MCP server?+

Retentioneering-tools is a Python toolkit and MCP server for reproducible clickstream and event log analytics. The MCP server exposes eventstream objects to AI agents like Claude, enabling them to explore user flows, run behavioral analyses, and generate validated HTML reports with auditable computations.

How do I install the Retentioneering MCP server?+

Install the package with 'pip install retentioneering' (Python 3.10+ required). To connect the MCP server to Claude Desktop or another MCP client, configure the client's JSON settings to invoke the Retentioneering MCP server command with the appropriate path to your eventstream data.

Which AI clients and environments work with Retentioneering?+

The Python toolkit runs in Jupyter, Google Colab, VS Code, Cursor, Claude Code, and any Python environment. The MCP server works with Claude Desktop and other MCP-compatible clients to enable agent-driven analytics.

Do I need API keys or external services to use Retentioneering?+

No API keys are required. Retentioneering runs entirely in your local environment; your event data never leaves your machine. You only need a DataFrame or file (CSV, Parquet, etc.) with user IDs, event names, and timestamps.

Is Retentioneering-tools free and open source?+

Yes, Retentioneering-tools is licensed under Apache-2.0 and free to use, modify, and build upon. Some proprietary Retentioneering products like managed services and enterprise integrations are separate commercial offerings.

What kind of data does Retentioneering analyze?+

Retentioneering analyzes clickstream, product event logs, and any timestamped behavioral data with a path identifier (user/session ID), event name, and timestamp. It accepts pandas DataFrames, CSV, TSV, Parquet, or exports from BigQuery, ClickHouse, and similar databases.

How do I install retentioneering-tools?+

Open the source repository on GitHub and follow its README. retentioneering-tools is a mcp server — MCP Agents Market links you directly to the official repo.

Is retentioneering-tools free?+

retentioneering-tools is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Analytics & Monitoring MCP ServersData Science & ML MCP ServersBest SkillsBest PluginsBest AgentsTop rated listingsClaude Code toolsBrowse all categories