convez.ai
MCP Server
thaolst

growth-mcp

thaolst/growth-mcp

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server for growth marketing - campaign design, retention analysis, churn prediction, A/B testing

Instalação

$npx convez-ai thaolst/growth-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
10
Forks
2
Acompanhando
0
Saúde
42%
Último commit
há 4 meses
Versão
v1.0.0
Issues abertas
0
Contribuidores
1

README

A tradução para o português deste README ainda está na fila.

Growth MCP

MCP server cho growth marketing - đóng gói domain knowledge thành tools Claude có thể gọi trực tiếp trong chat.

Tiếng Việt

Giải quyết vấn đề gì?

Growth PM thường mất thời gian làm đi làm lại các phân tích lặp: tính drop rate từ cohort data, nhớ intervention nào phù hợp budget nào, tra công thức sample size, design voucher theo segment...

growth-mcp đóng gói những logic này lại. Claude gọi trực tiếp trong chat, trả kết quả có thể dùng ngay - không còn trả lời chung chung.

Minh hoạ thực tế

1. Phân tích retention cohort

Bạn hỏi:

"Cohort tháng 3: week_0=100%, week_1=62%, week_2=41%, week_3=28%, week_4=21%. Budget nhỏ. Phân tích giúp mình."

Claude trả lời:

Drop lớn nhất ở W0→W1: 38% - đây là early activation problem, không phải retention problem. Retention về sau (W1→W2: 33.9%, W2→W3: 31.7%) thực ra khá ổn định.

Với budget S, nên tập trung vào W0→W1 trước:

  • In-app push reminder trong 24h đầu
  • Time-based trigger: nếu chưa quay lại sau 3 ngày → send offer
  • Streak mechanic nhỏ: visit 3 ngày liên tiếp = reward

2. Design campaign + voucher

Bạn hỏi:

"Muốn reactivate lapsed users (inactive 30-60 ngày, từng order ≥3 lần). Budget khoảng 100M. Nên làm gì?"

Claude trả lời:

Campaign level M - budget 50-200M VND, timeline 2-4 tuần. Channels: in-app push + paid social.

Với lapsed segment có lịch sử order tốt:

  • Fixed discount 40-50%, không min spend
  • Expiry 48 giờ - tạo urgency, không để họ "để mai"

3. Churn risk + điểm thưởng

Bạn hỏi:

"Segment này 45 ngày chưa active, 12.000 users, trung bình còn 320 điểm chưa dùng. Nguy cơ thế nào?"

Claude trả lời:

Medium risk - đang tiến gần ngưỡng churn. 320 điểm tích luỹ là hook tốt: nhắc điểm sắp hết hạn kết hợp offer nhỏ hiệu quả hơn discount đơn thuần.

4. Đọc kết quả A/B test

Bạn hỏi:

"Control 847 convert / 10.000 users, treatment 923 / 10.000. Có nên launch không?"

Claude trả lời:

Control: 8.47% → Treatment: 9.23% (+8.97% lift). Nhưng p = 0.058 → chưa significant.

Chưa nên launch. Cần thêm data. Nếu launch sớm, 6% chance đây là noise.

5. Tính sample size trước khi chạy test

Bạn hỏi:

"Conversion rate hiện tại 3.2%, muốn detect được lift 15%. Cần bao nhiêu users?"

Claude trả lời:

Cần 30.307 users/variant, tổng 60.614 users (power 90%, α=5%). Plan traffic trước, không chạy rồi mới tính.

Cài đặt

git clone https://github.com/thaolst/growth-mcp.git
cd growth-mcp
pip install -e .

Dùng với Claude Desktop

Thêm vào config file:

  • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "growth-mcp": {
      "command": "python",
      "args": ["-m", "growth_mcp.server"]
    }
  }
}

Restart Claude Desktop → chat bình thường, Claude tự gọi tool khi cần.

Dùng với Cursor

Thêm vào .cursor/mcp.json:

{
  "mcpServers": {
    "growth-mcp": {
      "command": "python",
      "args": ["-m", "growth_mcp.server"]
    }
  }
}

Tools

ToolLàm gìInput chính
design_campaignBrief campaign theo level S/M/Llevel, objective, segment
suggest_voucherVoucher phù hợp segmentsegment, objective, budget_level
optimize_voucherVoucher ladder 3 bậc kèm abuse riskavg_order_value_vnd, target_conversion_lift_pct, budget_per_user_vnd, voucher_type
inspect_csvXem cấu trúc file CSV: cột, kiểu dữ liệu, samplefile_path
analyze_experiment_from_csvA/B test trực tiếp từ CSV raw (1 dòng/user)file_path, group_col, converted_col
analyze_retention_from_csvPhân tích cohort retention từ CSV (rate hoặc count)file_path, period_col, value_col
summarize_segments_from_csvThống kê theo segment từ CSV rawfile_path, segment_col, value_col
analyze_experiment_from_bigqueryA/B test trên kết quả SQL BigQuerysql, group_col, converted_col
analyze_retention_from_bigqueryRetention cohort từ BigQuerysql, period_col, value_col
summarize_segments_from_bigqueryThống kê segment trên warehouse datasql, segment_col, value_col
monitor_campaignMonitor campaign real-timerun_days, reach, redemptions, vouchers, budget
analyze_segmentPhân tích segment + recommend targetingsegment_type, size, retention, redemption
analyze_retentionPhân tích cohort, tìm điểm dropcohort_data (JSON), campaign_level
predict_churn_riskĐánh giá nguy cơ churndays_inactive, users, points
analyze_experimentĐọc kết quả A/B testcontrol/treatment counts + sample sizes
estimate_sample_sizeTính sample size trước khi testbaseline_rate, MDE

Hệ sinh thái repo

Mình có 3 repo phục vụ 3 mục đích khác nhau:

RepoLà gìDùng khi nào
ai-growth-promptsThư viện prompt theo chủ đề, copy-paste được ngayCần prompt cho 1 task cụ thể: thiết kế voucher, phân tích segment, viết brief
ai-growth-agents-for-marketersWorkflow nhiều bước dạng prompt + script, có skill cài cho Claude CodeMuốn chạy quy trình end-to-end: lập kế hoạch MEU, phân tích A/B test
growth-mcp (repo này)MCP server đóng gói logic growth thành toolMuốn Claude/Cursor gọi tool trực tiếp thay vì paste prompt

Tool BigQuery cần extra dependency và auth chuẩn Google Cloud:

pip install "growth-mcp[bigquery]"
gcloud auth application-default login

Chỉ chấp nhận query SELECT (read-only), giới hạn 200K dòng. Data lớn hơn thì aggregate ngay trong SQL.

Giới hạn

Các tool phân tích nhận data qua tham số hoặc qua data layer CSV (*_from_csv). Đã hỗ trợ CSV và BigQuery. Mixpanel và các nguồn khác chưa có - export ra CSV rồi phân tích. Giúp tư duy nhanh hơn, không thay thế data analyst.

👤 Tác giả

Le Song Tien Thao (Tara) - Growth Marketer. Xây prompts, bots, và workflows cho growth marketing thực chiến.

🔗 LinkedIn · Facebook · X · Substack · Email

Nếu repo này hữu ích, star nhé ⭐

Growth MCP

MCP server for growth marketing - packaging domain knowledge into tools Claude can call directly in chat.

What problem does it solve?

Growth PMs often spend time repeating the same analyses: calculating drop rates from cohort data, remembering which interventions fit which budget, looking up sample size formulas, designing vouchers by segment...

growth-mcp packages this logic so Claude can call it directly in chat and return actionable output - not generic advice.

Real examples

1. Retention cohort analysis

You ask:

"March cohort: week_0=100%, week_1=62%, week_2=41%, week_3=28%, week_4=21%. Small budget. Analyse this."

Claude responds:

Biggest drop at W0→W1: 38% - this is an early activation problem, not a retention problem. Later-stage retention (W1→W2: 33.9%, W2→W3: 31.7%) is actually quite stable.

With a small budget, focus on W0→W1 first:

  • In-app push reminder within the first 24h
  • Time-based trigger: if no return after 3 days → send offer
  • Simple streak mechanic: visit 3 days in a row = reward

2. Campaign design + voucher

You ask:

"I want to reactivate lapsed users (inactive 30-60 days, had ≥3 orders). Budget around 100M. What should I do?"

Claude responds:

Campaign level M - budget 50-200M VND, timeline 2-4 weeks. Channels: in-app push + paid social.

For a lapsed segment with a strong order history:

  • Fixed discount 40-50%, no min spend
  • Expiry 48 hours - creates urgency

3. Churn risk + loyalty points

You ask:

"This segment hasn't been active for 45 days, 12,000 users, average 320 unused points. How at risk are they?"

Claude responds:

Medium risk - approaching the churn threshold. 320 accumulated points are a strong hook: reminding them their points are expiring combined with a small offer works better than a standalone discount.

4. Reading A/B test results

You ask:

"Control: 847 conversions / 10,000 users. Treatment: 923 / 10,000. Should I launch?"

Claude responds:

Control: 8.47% → Treatment: 9.23% (+8.97% lift). But p = 0.058 → not significant.

Don't launch yet. Need more data. If you launch now, there's a 6% chance this is noise.

5. Sample size before running a test

You ask:

"Current conversion rate is 3.2%, I want to detect a 15% lift. How many users do I need?"

Claude responds:

You need 30,307 users/variant, total 60,614 users (90% power, α=5%). Plan your traffic allocation before running, not after.

Installation

git clone https://github.com/thaolst/growth-mcp.git
cd growth-mcp
pip install -e .

Use with Claude Desktop

Add to your config file:

  • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "growth-mcp": {
      "command": "python",
      "args": ["-m", "growth_mcp.server"]
    }
  }
}

Restart Claude Desktop → chat normally, Claude calls tools automatically when needed.

Use with Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "growth-mcp": {
      "command": "python",
      "args": ["-m", "growth_mcp.server"]
    }
  }
}

Tools

ToolWhat it doesKey inputs
design_campaignCampaign brief by level S/M/Llevel, objective, segment
suggest_voucherVoucher recommendation by segmentsegment, objective, budget_level
optimize_voucher3-tier voucher ladder with abuse riskavg_order_value_vnd, target_conversion_lift_pct, budget_per_user_vnd, voucher_type
inspect_csvInspect CSV structure: columns, types, samplefile_path
analyze_experiment_from_csvA/B test straight from raw CSV (1 row/user)file_path, group_col, converted_col
analyze_retention_from_csvRetention cohort analysis from CSV (rates or counts)file_path, period_col, value_col
summarize_segments_from_csvPer-segment stats from raw CSVfile_path, segment_col, value_col
analyze_experiment_from_bigqueryA/B test on a BigQuery SQL resultsql, group_col, converted_col
analyze_retention_from_bigqueryRetention cohort from BigQuerysql, period_col, value_col
summarize_segments_from_bigquerySegment stats on warehouse datasql, segment_col, value_col
analyze_retentionCohort analysis, find biggest drop pointcohort_data (JSON), campaign_level
predict_churn_riskAssess churn risk leveldays_inactive, users, points
analyze_experimentRead A/B test results with statscontrol/treatment counts + sample sizes
estimate_sample_sizeCalculate sample size before running a testbaseline_rate, MDE

Repo ecosystem

I maintain 3 repos serving different purposes:

RepoWhat it isWhen to use
ai-growth-promptsTopic-based prompt library, ready to copy-pasteYou need a prompt for one specific task: voucher design, segment analysis, campaign brief
ai-growth-agents-for-marketersMulti-step workflows as prompts + scripts, installable as Claude Code skillsYou want an end-to-end process: MEU planning, A/B test analysis
growth-mcp (this repo)MCP server packaging growth logic as callable toolsYou want Claude/Cursor to call tools directly instead of pasting prompts

BigQuery tools need the optional dependency and standard Google Cloud auth:

pip install "growth-mcp[bigquery]"
gcloud auth application-default login

Read-only (SELECT queries only), capped at 200K rows. Aggregate in SQL for bigger data.

Limitations

Analysis tools take data via parameters or through the CSV data layer (*_from_csv). CSV and BigQuery are supported. Mixpanel and other sources are not yet - export to CSV first, then analyze. Meant to speed up thinking, not replace a data analyst.

👤 Author

Le Song Tien Thao (Tara) - Growth Marketer. Building prompts, bots, and workflows for real growth marketing work.

🔗 LinkedIn · Facebook · X · Substack · Email

If this is useful, star the repo ⭐

License

MIT - use freely, share widely.

Ver o original no GitHub

Bom para

Relacionados