📌Overview

Purpose: To provide a server for semantic analysis of chat conversations using vector embeddings and knowledge graphs.

Overview: The MCP Chat Analysis Server facilitates the analysis of chat data by enabling users to conduct semantic searches, extract concepts, and analyze conversation patterns. Through integration with existing systems, it offers comprehensive tools for understanding and navigating chat interactions.

Key Features:

Semantic Search: Enables users to find relevant messages and conversations by leveraging vector similarity, enhancing the searchability of chat content.
Knowledge Graph: Provides a navigable structure of relationships between messages, concepts, and topics, allowing for richer context and understanding of conversations.
Conversation Analytics: Analyzes various conversation metrics including patterns and dynamics, aiding in the evaluation and improvement of chat interactions.
Flexible Import: Supports multiple chat export formats for easy data ingestion and processing.
MCP Integration: Facilitates seamless integration with Claude and other MCP-compatible systems, ensuring versatility in deployment.

MCP Chat Analysis Server

A Model Context Protocol (MCP) server that enables semantic analysis of chat conversations through vector embeddings and knowledge graphs. This server provides tools for analyzing chat data, performing semantic search, extracting concepts, and analyzing conversation patterns.

Key Features

🔍 Semantic Search: Find relevant messages and conversations using vector similarity
🕸️ Knowledge Graph: Navigate relationships between messages, concepts, and topics
📊 Conversation Analytics: Analyze patterns, metrics, and conversation dynamics
🔄 Flexible Import: Support for various chat export formats
🚀 MCP Integration: Easy integration with Claude and other MCP-compatible systems

Quick Start

# Install the package
pip install mcp-chat-analysis-server

# Set up configuration
cp config.example.yml config.yml
# Edit config.yml with your database settings

# Run the server
python -m mcp_chat_analysis.server

MCP Integration

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "chat-analysis": {
      "command": "python",
      "args": ["-m", "mcp_chat_analysis.server"],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "NEO4J_URL": "bolt://localhost:7687",
        "NEO4J_USER": "neo4j",
        "NEO4J_PASSWORD": "your-password"
      }
    }
  }
}

Available Tools

import_conversations

Import and analyze chat conversations

{
    "source_path": "/path/to/export.zip",
    "format": "openai_native"  # or html, markdown, json
}

semantic_search

Search conversations by semantic similarity

{
    "query": "machine learning applications",
    "limit": 10,
    "min_score": 0.7
}

analyze_metrics

Analyze conversation metrics

{
    "conversation_id": "conv-123",
    "metrics": [
        "message_frequency",
        "response_times",
        "topic_diversity"
    ]
}

extract_concepts

Extract and analyze concepts

{
    "conversation_id": "conv-123",
    "min_relevance": 0.5,
    "max_concepts": 10
}

Architecture

See ARCHITECTURE.md for detailed diagrams and documentation of:

System components and interactions
Data flow and processing pipeline
Storage schema and vector operations
Tool integration mechanism

Prerequisites

Python 3.8+
Neo4j database for knowledge graph storage
Qdrant vector database for semantic search
sentence-transformers for embeddings

Installation

Install the package:

pip install mcp-chat-analysis-server

Set up databases:

# Using Docker (recommended)
docker compose up -d

Configure the server:

cp .env.example .env
# Edit .env with your settings

Development

Clone the repository:

git clone https://github.com/rebots-online/mcp-chat-analysis-server.git
cd mcp-chat-analysis-server

Install development dependencies:

pip install -e ".[dev]"

Run tests:

pytest tests/

Contributing

Fork the repository
Create a feature branch
Submit a pull request

See CONTRIBUTING.md for guidelines.

License

MIT License - See LICENSE file for details.

Related Projects

Support

📖 Documentation
🐛 Issue Tracker
💬 Discussions