MCP Chat Analysis Server
MCP聊天分析服务器
模型上下文协议 (MCP) 服务器,可通过向量嵌入和知识图谱对聊天对话进行语义分析。该服务器提供用于分析聊天数据、执行语义搜索、提取概念和分析对话模式的工具。
主要特点
🔍语义搜索:使用向量相似性查找相关消息和对话
🕸️知识图谱:导航消息、概念和主题之间的关系
📊对话分析:分析模式、指标和对话动态
🔄灵活导入:支持各种聊天导出格式
🚀 MCP 集成:轻松与 Claude 和其他 MCP 兼容系统集成
Related MCP server: Claude Conversation Logger
快速入门
# 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.serverMCP 集成
添加到您的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"
}
}
}
}可用工具
导入对话
导入并分析聊天对话
{
"source_path": "/path/to/export.zip",
"format": "openai_native" # or html, markdown, json
}语义搜索
按语义相似性搜索对话
{
"query": "machine learning applications",
"limit": 10,
"min_score": 0.7
}分析指标
分析对话指标
{
"conversation_id": "conv-123",
"metrics": [
"message_frequency",
"response_times",
"topic_diversity"
]
}提取概念
提取和分析概念
{
"conversation_id": "conv-123",
"min_relevance": 0.5,
"max_concepts": 10
}建筑学
有关以下详细图表和文档,请参阅ARCHITECTURE.md :
系统组件和交互
数据流和处理管道
存储模式和向量操作
工具集成机制
先决条件
Python 3.8+
Neo4j 数据库用于知识图谱存储
用于语义搜索的 Qdrant 矢量数据库
用于嵌入的句子转换器
安装
安装软件包:
pip install mcp-chat-analysis-server设置数据库:
# Using Docker (recommended)
docker compose up -d配置服务器:
cp .env.example .env
# Edit .env with your settings发展
克隆存储库:
git clone https://github.com/rebots-online/mcp-chat-analysis-server.git
cd mcp-chat-analysis-server安装开发依赖项:
pip install -e ".[dev]"运行测试:
pytest tests/贡献
分叉存储库
创建功能分支
提交拉取请求
请参阅CONTRIBUTING.md了解指南。
执照
MIT 许可证 - 有关详细信息,请参阅LICENSE文件。
相关项目
支持
This server cannot be deployed
Maintenance
Related MCP Connectors
Shared semantic graph for AI reviews, classification and structured memory across AI assistants.
Memory for deep conversational context across any platform
Knowledge graph ingestion, entity search, ontology analysis, and CoSync scoring.
Answer questions using your semantic layer and company knowledge graph.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceEnables AI assistants to enhance their responses with relevant documentation through a semantic vector search, offering tools for managing and processing documentation efficiently.15 npm65MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables intelligent conversation management with 4 AI agents that provide semantic analysis, pattern discovery, automatic documentation, and relationship mapping. Logs and analyzes Claude conversations with 70% token optimization and multi-language support.2-
- FlicenseCqualityDmaintenanceEnables AI assistants to analyze codebases through semantic search, call graph generation, and function metadata extraction. Provides real-time code analysis with persistent vector storage for understanding complex code structures and relationships.136-
- AlicenseBqualityNot gradedmaintenanceEnables semantic search across multiple knowledge datasets using FAISS vector embeddings, allowing natural language queries to find relevant documents with fast retrieval.21-