首页/MCP Server 目录/retentioneering/retentioneering-tools

retentioneering/retentioneering-tools

❌ 实测失败serverPythonApache-2.0★ 946

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 tests, process mining models, Markov chain simulation

实测结果

失败

沙箱内启动/握手失败，下方给出失败阶段与原始报错。失败阶段：—，错误类型：install_failed。这类信息对判断“是不是我这边的环境问题”很有用，原始报错见下。

error_type: install_failed

install timed out after 240s

安装方式: uvx
包名: retentioneering
解析依据: pyproject.toml name
沙箱: docker
总耗时: 240694 ms
安装耗时: 240693 ms
探针版本: 1.0.0
实测时间: 2026-11-11 14:47:56

如何使用

❌ 实测失败install_failed · install timed out after 240s；下面配置仅供参考，跑不跑得通取决于你的环境

1安装 / 启动命令uv / uvx

uvx retentioneering

2客户端配置Claude Desktop / Cursor

{
  "mcpServers": {
    "retentioneering-retentioneering-tools": {
      "command": "uvx",
      "args": [
        "retentioneering"
      ]
    }
  }
}

整段粘进 claude_desktop_config.json 的 mcpServers 里（Cursor 用 ~/.cursor/mcp.json），保存后重启客户端。

安装方式来源：pyproject.toml name，沙箱实测未通过。

打开 GitHub 仓库 ↗项目主页 ↗MCP 体检工具

仓库信息

全名: retentioneering/retentioneering-tools
分类: server
Stars: 946
Forks: 144
主要语言: Python
License: Apache-2.0
最近推送: 2026-11-08
仓库创建: 2019-07-02
首次收录: 2026-11-10
最近抓取: 2026-11-10

#agent-skills#analytics-mcp#behaviour-analysis#clickstream#clickstream-analysis#customer-journey-analytics#customer-journey-map#data-visualization#graph-visualizer#machine-learning#predictive-analytics#predictive-modeling