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

Tool	Làm gì	Input chính
`design_campaign`	Brief campaign theo level S/M/L	level, objective, segment
`suggest_voucher`	Voucher phù hợp segment	segment, objective, budget_level
`monitor_campaign`	Monitor campaign real-time	run_days, reach, redemptions, vouchers, budget
`analyze_segment`	Phân tích segment + recommend targeting	segment_type, size, retention, redemption
`analyze_retention`	Phân tích cohort, tìm điểm drop	cohort_data (JSON), campaign_level
`predict_churn_risk`	Đánh giá nguy cơ churn	days_inactive, users, points
`analyze_experiment`	Đọc kết quả A/B test	control/treatment counts + sample sizes
`estimate_sample_size`	Tính sample size trước khi test	baseline_rate, MDE

Giới hạn

Tool trả output dạng framework/recommendation, không kéo real data từ database. 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

Tool	What it does	Key inputs
`design_campaign`	Campaign brief by level S/M/L	level, objective, segment
`suggest_voucher`	Voucher recommendation by segment	segment, objective, budget_level
`analyze_retention`	Cohort analysis, find biggest drop point	cohort_data (JSON), campaign_level
`predict_churn_risk`	Assess churn risk level	days_inactive, users, points
`analyze_experiment`	Read A/B test results with stats	control/treatment counts + sample sizes
`estimate_sample_size`	Calculate sample size before running a test	baseline_rate, MDE

Limitations

Tools return framework-level output and recommendations - they don't pull real data from a database. 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.

Name		Name	Last commit message	Last commit date
Latest commit History 27 Commits
.github/workflows		.github/workflows
growth_mcp		growth_mcp
tests		tests
tools		tools
.gitignore		.gitignore
.python-version		.python-version
LICENSE		LICENSE
README.md		README.md
mcp-registry.json		mcp-registry.json
pyproject.toml		pyproject.toml

Folders and files

Latest commit

History

Repository files navigation

Growth MCP

Tiếng Việt

Giải quyết vấn đề gì?

Minh hoạ thực tế

1. Phân tích retention cohort

2. Design campaign + voucher

3. Churn risk + điểm thưởng

4. Đọc kết quả A/B test

5. Tính sample size trước khi chạy test

Cài đặt

Dùng với Claude Desktop

Dùng với Cursor

Tools

Giới hạn

👤 Tác giả

Growth MCP

What problem does it solve?

Real examples

1. Retention cohort analysis

2. Campaign design + voucher

3. Churn risk + loyalty points

4. Reading A/B test results

5. Sample size before running a test

Installation

Use with Claude Desktop

Use with Cursor

Tools

Limitations

👤 Author

License

About

Topics

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases 2

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

Packages