经 AI Skill Hub 精选评估,全渠道AI营销分析 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
基于dbt MetricFlo的现代数据栈,提供全渠道AI营销分析功能,帮助企业优化营销策略
全渠道AI营销分析 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
基于dbt MetricFlo的现代数据栈,提供全渠道AI营销分析功能,帮助企业优化营销策略
全渠道AI营销分析 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/eduardocornelsen/full-funnel-ai-analytics
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"---ai----": {
"command": "npx",
"args": ["-y", "full-funnel-ai-analytics"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 全渠道AI营销分析 执行以下任务... Claude: [自动调用 全渠道AI营销分析 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"___ai____": {
"command": "npx",
"args": ["-y", "full-funnel-ai-analytics"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Natural language marketing analytics powered by MCP, dbt Semantic Layer, and ML lead scoring. Works with Claude Desktop, OpenCode, Gemini CLI, and Antigravity IDE.
"Which channels actually drive revenue, not just clicks?"<br> This system answers that question in 15 seconds via natural language — backed by multi-touch attribution, a production ML scoring API, and dashboards fed from a single governed semantic layer running across 5 data warehouses.
---
python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt cp .env.example .env # Fill in your credentials
cd dbt_project && dbt build --target duckdb && cd ..
<details> <summary>Phase completion & project scale</summary>
| Phase | Status | Description |
|---|---|---|
| Phase 1: Data Foundation | ✅ Complete | Olist dataset + synthetic marketing data + warehouse loading |
| Phase 2: dbt Semantic Layer | ✅ Complete | 14 staging + 4 intermediate + 11 mart models |
| Phase 3: AI Layer (MCP) | ✅ Complete | 7 MCP servers + 4 AI client configs |
| Phase 4: ML Scoring | ✅ Complete | XGBoost + MLflow + FastAPI endpoint |
| Phase 5: Dashboards & Automation | ✅ Complete | Looker Studio + Streamlit + n8n routing |
| Phase 6: Portability & Polish | ✅ Complete | Snowflake/Databricks demos + documentation |
| Phase 7: Production Readiness & CI/CD | ✅ Complete | GitHub Actions, warehouse adapters, daily synthetic data, test suite, connector UI |
| Component | Detail |
|---|---|
| **Data Volume** | 23 CSV files, **2.2M+ rows**, aligned across 2024–2026 |
| **DuckDB Warehouse** | **46 objects** (staging views + mart tables), all populated |
| **dbt Models** | **29 models**, all materialized, end-to-end verified |
| **MCP Servers** | **7 servers**, column references cross-checked against source CSVs |
| **Streamlit App** | 5 tabs + Data Sources page, all DuckDB queries valid, AI analyst integrated |
| **ML Pipeline** | XGBoost trained on **93K rows**, FastAPI /score endpoint live |
| **Semantic Layer** | **5 semantic models** + **13+ metrics** governed |
| **CI/CD Workflows** | **4 GitHub Actions workflows** — PR gate, warehouse deploy, scheduled refresh, daily synthetic data |
| **Test Suite** | **20+ pytest assertions** on golden metrics + FastAPI endpoint |
| **Dependencies** | **27 core packages**, all importable |
</details>
---
See the Step-by-Step Setup Guide for full instructions.
```bash
Predefined commands: type /marketing and see the magic happens:

View the dashboards for all commands available: <br> [[/marketing]](dashboards/full_funnel_marketing_dashboard.html) | [[/attribution]](dashboards/attribution_dashboard.html) | [[/campaign]](dashboards/campaign_performance_dashboard.html) | [[/pipeline]](dashboards/pipeline_dashboard.html) | [[/traffic]](dashboards/traffic_ga4_dashboard.html)
cd api && uvicorn main:app --port 8000 &
| Workflow | Trigger | What it does |
|---|---|---|
[ci.yml](.github/workflows/ci.yml) | Every pull request | dbt compile + test on DuckDB → generate golden metrics → validate drift → pytest. No cloud creds needed. |
[warehouse-deploy.yml](.github/workflows/warehouse-deploy.yml) | Push to main | Deploys dbt to BigQuery **and** Snowflake in parallel → regenerates golden_metrics.json → commits it back to the repo. |
[scheduled-refresh.yml](.github/workflows/scheduled-refresh.yml) | Daily 06:00 UTC | Appends synthetic data → dbt run/test → regenerates golden metrics with --live flag → validates. |
[daily-synthetic-data.yml](.github/workflows/daily-synthetic-data.yml) | Daily 05:00 UTC | Adds one new day of realistic synthetic data to mock CSVs. Can be manually triggered with a custom --days count. |
```
---
该工具基于dbt MetricFlo,提供现代数据栈和全渠道AI营销分析功能,帮助企业优化营销策略,但需要进一步优化和完善
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:全渠道AI营销分析 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | full-funnel-ai-analytics |
| 原始描述 | 开源MCP工具:Full-Funnel AI Marketing Analytics. A modern data stack powered by dbt MetricFlo。⭐10 · Python |
| Topics | mcpagentsai-analytics |
| GitHub | https://github.com/eduardocornelsen/full-funnel-ai-analytics |
| License | MIT |
| 语言 | Python |
收录时间:2026-05-23 · 更新时间:2026-05-23 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端