SunflowersLwtech/mcp_creator_growth

๐Ÿค– Coding Agents
0 Views
0 Installs

๐Ÿ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Intelligent learning sidecar for AI coding assistants. Helps developers learn from AI-generated code changes through interactive blocking quizzes and provides agents with persistent project-specific debugging memory using silent RAG tools. Features 56% token optimization and multi-language support.

Quick Install

One-Click IDE Configuration
claude_desktop_config.json
{
  "mcpServers": {
    "sunflowerslwtech-mcp-creator-growth": {
      "command": "npx",
      "args": [
        "-y",
        "sunflowerslwtech-mcp-creator-growth"
      ]
    }
  }
}
Or

Using an AI coding agent (Claude Code, Cursor, etc.)? Copy a ready-made prompt that tells it to fetch the setup instructions and install this server for you.

Documentation Overview

MCP Creator Growth

English | ็ฎ€ไฝ“ไธญๆ–‡ | ็น้ซ”ไธญๆ–‡

A context-aware Model Context Protocol (MCP) server that acts as a learning sidecar for AI coding assistants. It helps developers learn from AI-generated code changes through interactive quizzes and provides agents with a persistent project-specific debugging memory.

License: MIT Python 3.11+ MCP Standard Docker Glama MCP DeepWiki


๐ŸŒ Resources

ResourceDescription
Glama MCP MarketplaceOfficial MCP server listing with installation guides
DeepWiki DocumentationAI-generated deep analysis of the codebase
GitHub RepositorySource code, issues, and contributions

๐Ÿš€ Why Use This?

ForBenefit
DevelopersDon't just accept AI codeโ€”understand it. Request a quiz to verify your grasp of the logic, security, or performance implications.
AI AgentsStop solving the same bug twice. The server quietly records debugging solutions and retrieves them automatically when similar errors occur.

๐Ÿ“ฆ Available Tools

ToolTypeDescription
learning_session๐ŸŽ“ InteractiveOpens a WebUI quiz based on recent code changes. Blocks until user completes learning.
debug_search๐Ÿ” Silent RAGSearches project debug history for relevant past solutions. Auto-triggered on errors.
debug_record๐Ÿ“ SilentRecords debugging experiences to project knowledge base. Auto-triggered after fixes.
term_get๐Ÿ“š ReferenceFetches programming terms/concepts. Tracks shown terms to avoid repetition.

Tool Details

๐ŸŽ“ learning_session - Interactive Learning Card

Trigger: User explicitly requests (e.g., "Quiz me", "Test my understanding")

Parameters:

ParameterTypeDefaultDescription
project_directorystring"."Project directory path
summarystringโ€”Structured summary of Agent's actions
reasoningobjectnull5-Why reasoning (goal, trigger, mechanism, alternatives, risks)
quizzesarrayauto-generated3 quiz questions with options, answer, explanation
focus_areasarray["logic"]Focus areas: logic, security, performance, architecture, syntax
timeoutint600Timeout in seconds (60-7200)

Returns: {"status": "completed", "action": "HALT_GENERATION"}

๐Ÿ” debug_search - Search Debug History

Trigger: Auto-called when encountering errors (silent, no UI)

Parameters:

ParameterTypeDefaultDescription
querystringโ€”Error message or description to search
project_directorystring"."Project directory path
error_typestringnullFilter by error type (e.g., ImportError)
tagsarraynullFilter by tags
limitint5Maximum results (1-20)

Returns: {"results": [...], "count": N}

๐Ÿ“ debug_record - Record Debug Experience

Trigger: Auto-called after fixing bugs (silent, background)

Parameters:

ParameterTypeDefaultDescription
contextobjectโ€”Error context: {error_type, error_message, file, line}
causestringโ€”Root cause analysis
solutionstringโ€”Solution that worked
project_directorystring"."Project directory path
tagsarraynullTags for categorization

Returns: {"ok": true, "id": "..."}

๐Ÿ“š term_get - Get Programming Terms

Available Domains: programming_basics, data_structures, algorithms, software_design, web_development, version_control, testing, security, databases, devops

Parameters:

ParameterTypeDefaultDescription
project_directorystring"."Project directory path
countint3Number of terms (1-5)
domainstringnullFilter by domain

Returns: {"terms": [...], "count": N, "remaining": N}


๐Ÿ› ๏ธ Installation

One-Line Install (Recommended)

PlatformCommand
macOS / Linux
curl -fsSL https://raw.githubusercontent.com/SunflowersLwtech/mcp_creator_growth/main/scripts/install.sh | bash
Windows (PowerShell)
irm https://raw.githubusercontent.com/SunflowersLwtech/mcp_creator_growth/main/scripts/install.ps1 | iex

The installer will:

  1. Auto-detect your Python environment (uv โ†’ conda โ†’ venv)
  2. Clone the repository to ~/mcp-creator-growth
  3. Create virtual environment and install dependencies
  4. Print the exact command to configure your IDE

Manual Installation

Click to expand manual installation steps

Prerequisites: Python 3.11+ or uv

# 1. Clone the repository
git clone https://github.com/SunflowersLwtech/mcp_creator_growth.git
cd mcp_creator_growth

# 2. Create virtual environment and install
# Using uv (recommended)
uv venv --python 3.11 mcp-creator-growth
source mcp-creator-growth/bin/activate          # macOS/Linux
# mcp-creator-growth\Scripts\activate           # Windows
uv pip install -e '.[dev]'

# Or using standard venv
python -m venv mcp-creator-growth
source mcp-creator-growth/bin/activate           # macOS/Linux
# mcp-creator-growth\Scripts\activate            # Windows
pip install -e '.[dev]'

Docker Installation

Click to expand Docker installation steps

Prerequisites: Docker installed on your system

# 1. Pull from Docker Hub
docker pull sunflowerslwtech/mcp-creator-growth:latest

# Or build locally
git clone https://github.com/SunflowersLwtech/mcp_creator_growth.git
cd mcp_creator_growth
docker build -t mcp-creator-growth .

# 2. Run with Docker
docker run -i mcp-creator-growth

# 3. Or use Docker Compose
docker-compose up -d

For detailed Docker usage, persistent storage, and Claude Desktop integration, see DOCKER.md.


โš™๏ธ IDE Configuration

Claude Code (CLI) โ€” One Command Setup

After installation, configure your AI coding IDE to use this MCP server.

Claude Code

Option 1: CLI (Recommended)

# macOS / Linux
claude mcp add mcp-creator-growth -- ~/mcp-creator-growth/mcp-creator-growth/bin/mcp-creator-growth

# Windows
claude mcp add mcp-creator-growth -- %USERPROFILE%\mcp-creator-growth\mcp-creator-growth\Scripts\mcp-creator-growth.exe

Option 2: Config File

Add to ~/.claude.json:

{
  "mcpServers": {
    "mcp-creator-growth": {
      "command": "~/mcp-creator-growth/mcp-creator-growth/bin/mcp-creator-growth"
    }
  }
}

For Windows:

{
  "mcpServers": {
    "mcp-creator-growth": {
      "command": "C:\\Users\\YourName\\mcp-creator-growth\\mcp-creator-growth\\Scripts\\mcp-creator-growth.exe"
    }
  }
}

Example paths:

  • Unix (uv): ~/mcp-creator-growth/mcp-creator-growth/bin/mcp-creator-growth
  • Windows (uv): C:\\Users\\YourName\\mcp-creator-growth\\mcp-creator-growth\\Scripts\\mcp-creator-growth.exe
  • Windows (conda): C:\\Users\\YourName\\anaconda3\\envs\\mcp-creator-growth\\Scripts\\mcp-creator-growth.exe

Path breakdown (Unix example):

  • ~/mcp-creator-growth โ†’ repository directory
  • mcp-creator-growth โ†’ virtual environment directory created by uv/venv
  • bin/mcp-creator-growth โ†’ executable

Cursor

Add to Cursor MCP settings (Settings โ†’ MCP โ†’ Add Server):

{
  "mcp-creator-growth": {
    "command": "~/mcp-creator-growth/mcp-creator-growth/bin/mcp-creator-growth"
  }
}

For Windows:

{
  "mcp-creator-growth": {
    "command": "C:\\Users\\YourName\\mcp-creator-growth\\mcp-creator-growth\\Scripts\\mcp-creator-growth.exe"
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "mcp-creator-growth": {
      "command": "~/mcp-creator-growth/mcp-creator-growth/bin/mcp-creator-growth"
    }
  }
}

Docker Configuration

To use Docker with any MCP-compatible IDE:

{
  "mcpServers": {
    "mcp-creator-growth": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/path/to/your/project:/workspace",
        "-w",
        "/workspace",
        "mcp-creator-growth"
      ]
    }
  }
}

See DOCKER.md for detailed Docker configuration examples for Claude Desktop, Cursor, and other IDEs.

Other IDEs

For any MCP-compatible IDE, use these settings:

  • Command: <install-path>/mcp-creator-growth/bin/mcp-creator-growth (or mcp-creator-growth\Scripts\mcp-creator-growth.exe on Windows)
  • Transport: stdio

After configuration, restart your IDE.

Usage

Available Tools

ToolTriggerForReturns
learning_sessionUser explicit requestUser{status, action} - minimal
debug_searchAutomatic (on error)AgentCompact summaries
debug_recordAutomatic (after fix)Agent{ok, id} - minimal

For Users: Learning Session

Say to your AI assistant:

  • "Quiz me on this change"
  • "Test my understanding"
  • "Help me learn about what you did"

The agent will create an interactive learning card and wait until you complete it.

Note: Quiz scores are saved locally for your self-tracking but are NOT returned to the agent - this keeps the context clean.

For Agents: Debug Tools

The debug tools work silently in the background:

  • Search first: When encountering errors, agent searches past solutions
  • Record after: When fixing errors, agent records the solution
  • Progressive disclosure: Returns compact summaries, not full records
  • Fast lookups: Uses inverted index for keyword-based searches

Updating

One-Line Update (Recommended)

The remote update script automatically detects your installation and works with any path format (including Chinese/non-ASCII paths):

macOS / Linux
curl -fsSL https://raw.githubusercontent.com/SunflowersLwtech/mcp_creator_growth/main/scripts/update.sh | bash
Windows (PowerShell)
irm https://raw.githubusercontent.com/SunflowersLwtech/mcp_creator_growth/main/scripts/update.ps1 | iex

The update script will:

  1. Auto-detect your installation location (supports multiple installations)
  2. Pull the latest changes from the repository
  3. Force-reinstall dependencies to ensure version synchronization
  4. Verify installation integrity and report any issues
  5. Detect if MCP server is in use and provide clear instructions

Why remote update?

  • โœ… Works with Chinese/non-ASCII paths without cd navigation
  • โœ… Always uses the latest update logic from the repository
  • โœ… Auto-detects installation location even if you forgot where it is
  • โœ… Handles multiple installations gracefully

Local Update (Alternative)

macOS / Linux:

~/mcp-creator-growth/scripts/update.sh

Windows (PowerShell):

~\mcp-creator-growth\scripts\update.ps1

Manual Update

Click to expand manual update steps
# Navigate to installation directory
cd ~/mcp-creator-growth  # or your custom installation path

# Pull latest changes
git pull origin main

# Update dependencies
# Using uv
source mcp-creator-growth/bin/activate          # macOS/Linux
# mcp-creator-growth\Scripts\activate           # Windows
uv pip install -e '.[dev]' --upgrade

# Or using standard venv
source mcp-creator-growth/bin/activate           # macOS/Linux
# mcp-creator-growth\Scripts\activate            # Windows
pip install -e '.[dev]' --upgrade

๐Ÿ–ผ๏ธ Screenshots

Learning Session WebUI

WebUI Preview


๐Ÿ”’ Security & Privacy

AspectDetails
Local FirstAll data stored in .mcp-sidecar/ directory within your project
No TelemetryZero data sent to external servers
Full ControlDelete .mcp-sidecar/ anytime to reset all data

๐Ÿ”ฎ Roadmap

We're building toward a Personalized Learning Center that grows with you. Here's what's coming:

๐Ÿ” Advanced Search & Indexing (v1.2)

FeatureDescription
SQLite FTS5Full-text search with Chinese support, prefix matching, and boolean queries
BM25 RankingIndustry-standard relevance scoring for better search results
Semantic SearchVector embeddings for meaning-based matching (e.g., "ๆƒ้™้”™่ฏฏ" finds "permission denied")
Cross-project SearchSearch debug experiences across all your projects

๐Ÿ“ฑ Mobile App (v2.0)

FeatureDescription
Learning History SyncAccess your quiz history and learning progress on mobile
Spaced RepetitionSmart review scheduling based on forgetting curves
Offline ModeLearn anywhere, sync when connected
Push NotificationsGentle reminders to review concepts you're forgetting

๐ŸŽฏ Personalized Learning Center (v2.5)

FeatureDescription
Knowledge GraphVisual map of concepts you've learned and their connections
Weakness AnalysisAI identifies areas where you struggle and suggests focused practice
Learning StreaksGamification to keep you motivated
Team Insights(Optional) Share anonymized learning patterns with your team

๐Ÿค– AI Enhancements (v3.0)

FeatureDescription
Adaptive QuizzesQuestions adjust difficulty based on your performance
Code Pattern RecognitionLearn from patterns in your own codebase
Multi-language SupportExplanations in your preferred language
Voice Interface"Hey Claude, quiz me on what we did yesterday"

Want to influence the roadmap? Open an issue or join the discussion!


๐Ÿ”ง Environment Variables

VariableDefaultDescription
MCP_DEBUGfalseEnable debug logging (true, 1, yes, on)
MCP_TIMEOUT120000MCP server startup timeout in ms
MAX_MCP_OUTPUT_TOKENS25000Maximum tokens for MCP output

๐Ÿค Contributing

We welcome contributions! Please follow these steps:

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/amazing-feature
  3. Install dev dependencies: uv pip install -e '.[dev]'
  4. Make changes and run tests: pytest
  5. Submit a Pull Request

See CONTRIBUTING.md for detailed guidelines.


๐Ÿ“ฌ Contact

ChannelAddress
Emailsunflowers0607@outlook.com
Emailweiliu0607@gmail.com
GitHub IssuesOpen an Issue

๐Ÿ“„ License

This project is licensed under the MIT License.


Built with FastMCP โ€ข MCP Standard โ€ข Glama MCP

Related MCP Servers

5dive-ai/5dive-mcp

๐Ÿ“‡ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Manage a 5dive agent fleet from any MCP client: file tasks, message and inspect agents, and read the fleet digest. Thin adapter over the 5dive CLI.

๐Ÿค– Coding Agents0 views
agent-blueprint/mcp-server

๐Ÿ“‡ โ˜๏ธ - 8 MCP tools for exploring and downloading AI agent blueprints. List blueprints, get summaries, download full Agent Skills directories for implementation by coding agents. Vendor-agnostic output works with any enterprise platform. Install: npx agentblueprint.

๐Ÿค– Coding Agents0 views
agentic-mcp-tools/owlex

๐Ÿ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - AI council server: query CLI agents (Claude Code, Codex, Gemini, and OpenCode) in parallel with deliberation rounds

๐Ÿค– Coding Agents0 views
alpadalar/netops-mcp

๐Ÿ ๐Ÿ  - Comprehensive DevOps and networking MCP server providing standardized access to essential infrastructure tools. Features network monitoring, system diagnostics, automation workflows, and infrastructure management with AI-powered operational insights.

๐Ÿค– Coding Agents0 views

Engagement

Views
0
Installs
0
Upvotes
0

Views and upvotes are unique per visitor network (hashed IP). Installs count copy actions.

Status

Health: Not checked yet

We have not completed a health check for this listing yet.

No check timestamp yet.

Unclaimed listing (imported or pending owner verification). Claim it โ†’
โ˜… Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to get the verified badge and attach your website.

Claim this listing

Promote this listing

Optional paid placement. Free listings stay free forever.

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.