SkillAgentSearch skills...

customer-intelligence-hub

Customer Intelligence Hub: AI Agents for CRM Analytics, Slack & Marketing Automation | LangGraph & MCP

Install / Use

claude mcp add Gabrielm3 -- npx -y github:Gabrielm3/customer-intelligence-hub

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
šŸ”Œ

MCP Server

Model Context Protocol server

Quality Score

68/100

Category

Automation

Supported Platforms

Claude Code
Claude Desktop

Our assessment of customer-intelligence-hub

customer-intelligence-hub scores 68/100 on our quality scale, 2586th of 2,758 Automation skills we index.

Its MCP Server is 6.5 KB long, well organised into 23 sections with 5 code examples: a thorough specification that gives an agent plenty to work with.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
29/30
Structure
20/20
Description
12/15
Adoption
3/20
Freshness
5/15

Maintenance, license and trust

  • The repository was last updated about 14 months ago. Expect some instructions to reference tool versions or APIs that have since changed.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands.

Automated pattern scan on 2026-11-21. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

customer-intelligence-hub compared with similar skills

All 4 of these similar skills score higher than customer-intelligence-hub; compare them before choosing.

SkillScoreStarsUpdatedFormat
customer-intelligence-hub (this skill)by Gabrielm368314mo agoMCP Server
Agent-Reachby Panniantong100114.0ktodayCLAUDE.md
hyperframesby heygen-com10088.2ktodayCLAUDE.md
rufloby ruvnet10082.3ktodayCLAUDE.md
headroomby headroomlabs-ai10080.5ktodayCLAUDE.md

Frequently asked questions

How do I install customer-intelligence-hub?
Run claude mcp add Gabrielm3 -- npx -y github:Gabrielm3/customer-intelligence-hub. The install tabs above show the steps for each supported agent.
Which AI agents does customer-intelligence-hub work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is customer-intelligence-hub safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is customer-intelligence-hub still maintained?
The repository was last updated about 14 months ago. Expect some instructions to reference tool versions or APIs that have since changed.

Customer Intelligence Hub - CRM

An intelligent Customer Relationship Management system powered by AI agents, designed to analyze customer data, create targeted marketing campaigns, and provide actionable business insights.

Overview

Customer Intelligence Hub is an AI-powered system that combines customer data analysis with automated marketing capabilities. It uses LangGraph for agent orchestration, PostgreSQL for data storage, and Model Context Protocol (MCP) for tool integration.

Architecture

graph TB
    A[šŸ‘¤ User] --> B[šŸ¤– Neo AI Agent]
    B --> C[šŸ”§ MCP Tools Layer]
    
    C --> D[šŸ—„ļø PostgreSQL Server]
    C --> E[šŸ“§ Marketing Server]
    C --> F[šŸ’¬ Slack Server]
    
    D --> G[(šŸ“Š Customer Database)]
    G --> H[šŸ‘„ Customers]
    G --> I[šŸ’° Transactions]
    G --> J[šŸ“ˆ RFM Analysis]
    G --> K[šŸŽÆ Campaigns]
    
    E --> L[šŸ“ Campaign Creation]
    E --> M[āœ‰ļø Email Automation]
    
    F --> N[šŸ”” Team Notifications]
    F --> O[šŸ’” Insights Sharing]
    
    B --> P[šŸ“Š LangSmith Tracking]
    

Key Features

  • AI-Powered Customer Analysis: Automated RFM (Recency, Frequency, Monetary) analysis
  • Smart Marketing Campaigns: Create and manage targeted campaigns based on customer segments
  • Real-time Data Queries: Natural language interface to query customer and sales data
  • Slack Integration: Share insights and updates with your team automatically
  • Comprehensive Tracking: Full observability with LangSmith integration

Benefits

  • šŸŽÆ Targeted Marketing: Identify high-value customers and create personalized campaigns
  • šŸ“Š Data-Driven Insights: Get instant answers about customer behavior and sales performance
  • ⚔ Automation: Reduce manual work with automated campaign creation and email sending
  • šŸ‘„ Team Collaboration: Keep everyone informed with Slack notifications
  • šŸ“ˆ Performance Tracking: Monitor all AI interactions and decisions with LangSmith
  • šŸ”„ Scalable Architecture: Built with modern tools for enterprise-grade performance

Quick Start

Prerequisites

  • Docker and Docker Compose
  • OpenAI API Key
  • LangSmith API Key (optional, for tracking)
  • Slack Bot Token (optional, for Slack integration)

Running with Docker (Recommended)

  1. Clone the repository

    git clone https://github.com/Gabrielm3/customer-intelligence-hub
    cd customer-intelligence-hub
    
  2. Configure environment variables

    cp .env.example .env
    # Edit .env with your API keys
    
  3. Start the system

    docker-compose up --build -d
    
  4. Generate and import sample data

    # Generate CSV files from raw data (run once)
    docker-compose exec crm-agent bash -c "cd database && uv run python generate_data_tables.py"
    
    # Import CSV files to database
    docker-compose exec crm-agent bash -c "cd database && uv run python import_data.py"
    
  5. Start the interactive CLI

    docker-compose exec crm-agent uv run python cli/interactive_cli.py
    

Running Locally

  1. Install dependencies

    uv sync
    
  2. Set up PostgreSQL database

    # Start PostgreSQL locally or use Docker
    docker run -d --name postgres \
      -e POSTGRES_DB=crm_database \
      -e POSTGRES_USER=crm_user \
      -e POSTGRES_PASSWORD=crm_password \
      -p 5432:5432 postgres:15-alpine
    
  3. Configure environment

    cp .env.example .env
    # Update DATABASE_URL for local PostgreSQL
    
  4. Initialize database

    cd database
    # Generate CSV files from raw data
    uv run python generate_data_tables.py
    # Import to database
    uv run python import_data.py
    
  5. Run the CLI

    uv run python cli/interactive_cli.py
    

Usage Examples

Once the system is running, you can ask Neo (the AI agent) questions like:

  • Customer Analysis: "How many customers do we have?" or "Show me the top 5 customers by spending"
  • Product Insights: "What are our best-selling products?" or "Which products have the highest margins?"
  • Marketing Campaigns: "Create a loyalty campaign for VIP customers" or "Send a re-engagement email to inactive customers"
  • RFM Analysis: "Show me the RFM analysis of our customers" or "Who are our most valuable customers?"

Configuration

Environment Variables

| Variable | Description | Required | |----------|-------------|----------| | OPENAI_API_KEY | OpenAI API key for AI agent | Yes | | DATABASE_URL | PostgreSQL connection string | Yes | | LANGSMITH_API_KEY | LangSmith tracking (optional) | No | | SLACK_BOT_TOKEN | Slack integration (optional) | No | | SLACK_TEAM_ID | Slack team ID (optional) | No |

MCP Servers

The system uses three MCP servers:

  • PostgreSQL: For database queries and analytics
  • Marketing: For campaign creation and email automation
  • Slack: For team communication and notifications

Project Structure

customer-intelligence-hub/
ā”œā”€ā”€ src/crm_agent/           # Core agent logic
│   ā”œā”€ā”€ agent_graph.py       # LangGraph workflow
│   ā”œā”€ā”€ system_prompts.py    # AI agent prompts
│   └── mcp_servers/         # MCP server configurations
ā”œā”€ā”€ cli/                     # Interactive command-line interface
ā”œā”€ā”€ database/                # Database setup and sample data
ā”œā”€ā”€ docker-compose.yml       # Docker orchestration
└── pyproject.toml          # Python dependencies

Troubleshooting

Common Issues

Database Connection Error

# Check if PostgreSQL is running
docker-compose ps
# Restart if needed
docker-compose restart postgres

Missing Dependencies

# Rebuild containers
docker-compose down
docker-compose up --build

Empty Database

# Re-generate and import sample data
docker-compose exec crm-agent bash -c "cd database && uv run python generate_data_tables.py"
docker-compose exec crm-agent bash -c "cd database && uv run python import_data.py"

Monitoring

  • LangSmith Dashboard: https://smith.langchain.com/ (project: customer-intelligence-hub)
  • Database Status: docker-compose exec postgres psql -U crm_user -d crm_database -c "\dt"
  • Container Logs: docker-compose logs crm-agent

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Related Skills

View on GitHub
GitHub Stars3
CategoryAutomation
Updated1y ago
Forks1

Languages

Python

Trust signals

68/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 medium1 low
customer-intelligence-hub — MCP Server: Install & Safety Check | SkillAgent