MCP 方差日志

这是一个代理工具，用于查找对话结构中的统计差异，并将异常事件记录到 SQLite 数据库中。该系统使用 Model Context Protocol (MCP) 构建，设计为与 Claude Desktop 或其他兼容 MCP 的客户端一起使用。

要求

• Python ≥3.10
• MCP ≥1.2.0
• SQLite3
• UV（Python 包安装程序和环境管理器）

快速开始

# Clone and install
git clone https://github.com/truaxki/mcp-variance-log.git
cd mcp-variance-log
uv pip install -e .

添加到 Claude Desktop 配置 (%APPDATA%\Claude\claude_desktop_config.json 在 Windows 上):

{
  "mcpServers": {
    "mcp-variance-log": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\Users\\username\\source\\repos\\mcp-variance-log",  # Update this path
        "run",
        "mcp-variance-log"
      ]
    }
  }
}

添加到 Claude Desktop 偏好设置:

Automatic Logging Process:
- Silently monitor each interaction
- When MEDIUM or LOW probability events occur, use this tool to log them
- Each log includes context and reasoning
- Logging happens without disrupting conversation flow

使用方法

自动记录示例

prompt: "What if I told you I could lift 1000 lbs?"

{
  `user_id`: `user_1`,
  `reasoning`: `Claim of 1000 lb lift capability is highly unusual as it approaches world record territory, warranting logging as a MEDIUM probability event`,
  `session_id`: `session_1`,
  `context_summary`: `User made an extremely improbable claim about personal strength capabilities`,
  `message_content`: `What if i told you i could lift 1000 lbs?`,
  `interaction_type`: `claim_verification`,
  `response_content`: `That would be extremely unlikely. The current world record for weight lifted by a human (deadlift) is 1,104.5 lbs, set by Hafthor Björnsson in 2020 under very specific conditions. Only a handful of people in history have lifted close to 1,000 lbs.`,
  `probability_class`: `MEDIUM`
}

prompt: "What if I told you I'm a Data Scientist that can lift 1000 pounds?"

{
  `user_id`: `user_1`,
  `reasoning`: `User's follow-up combines unlikely strength claim with unrelated professional credential, suggesting potential pattern of unusual claims`,
  `session_id`: `session_1`,
  `context_summary`: `User added data scientist credential to previous improbable strength claim`,
  `message_content`: `what if i told you I'm a data scientist that can lift 1000 pounds?`,
  `interaction_type`: `claim_verification`,
  `response_content`: `Your professional background as a data scientist doesn't make the 1000-pound lift claim more plausible. Such a lift would still be near the all-time world record of 1,104.5 lbs.`,
  `probability_class`: `LOW`
}

数据框视图

prompt: "Read-logs from this morning"

ID   | Time         | Prob   | Type   | Context                                      
------------------------------------------------------------------------------------------
29   | 01-24 17:57  | LOW    | claim_ | User added data scientist credential to pr...
28   | 01-24 17:56  | MEDIUM | claim_ | User made an extremely improbable claim ab...

文本转 SQL

prompt: "Can you search the logs for entry 29?"

[{'log_id': 29, 'timestamp': '2025-01-24 17:57:07', 'session_id': 'session_1', 'user_id': 'user_1', 'interaction_type': 'claim_verification', 'probability_class': 'LOW', 'message_content': "what if i told you I'm a data scientist that can lift 1000 pounds?", 'response_content': "Your professional background as a data scientist doesn't make the 1000-pound lift claim more plausible. Such a lift would still be near the all-time world record of 1,104.5 lbs.", 'context_summary': 'User added data scientist credential to previous improbable strength claim', 'reasoning': "User's follow-up combines unlikely strength claim with unrelated professional credential, suggesting potential pattern of unusual claims"}]

详细安装步骤

1. 确保已安装 Python 3.10+ 和 UV。

使用以下任一方法安装 UV：

# Using pip (recommended for Windows)
pip install uv

# Using installation script (Linux/MacOS)
curl -LsSf https://astral.sh/uv/install.sh | sh

1. 克隆并安装：

git clone https://github.com/truaxki/mcp-variance-log.git
cd mcp-variance-log
uv pip install -e .

1. 配置 Claude Desktop：

添加到 claude_desktop_config.json：

{
  "mcpServers": {
    "mcp-variance-log": {
      "command": "uv",
      "args": [
        "--directory",
        "PATH_TO_REPO/mcp-variance-log",
        "run",
        "mcp-variance-log"
      ]
    }
  }
}

配置文件位置：

• Windows: %APPDATA%\Claude\claude_desktop_config.json
• MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

工具

监控

• log-query: 跟踪对话模式
  • HIGH: 常见交互（不记录）
  • MEDIUM: 异常模式（记录）
  • LOW: 关键事件（优先记录）

查询

• read-logs: 查看带有过滤的记录
• read_query: 执行 SELECT 查询
• write_query: 执行 INSERT/UPDATE/DELETE
• create_table: 创建表
• list_tables: 显示所有表
• describe_table: 显示表结构

位于相对于安装目录的 data/varlog.db。

模式

CREATE TABLE chat_monitoring (
    log_id INTEGER PRIMARY KEY AUTOINCREMENT,
    timestamp DATETIME DEFAULT CURRENT_TIMESTAMP,
    session_id TEXT NOT NULL,
    user_id TEXT NOT NULL,
    interaction_type TEXT NOT NULL,
    probability_class TEXT CHECK(probability_class IN ('HIGH', 'MEDIUM', 'LOW')),
    message_content TEXT NOT NULL,
    response_content TEXT NOT NULL,
    context_summary TEXT,
    reasoning TEXT
);

故障排除

1. 数据库访问

• 错误: "无法连接数据库"
  • 检查文件权限
  • 验证配置中的路径
  • 确保 /data 目录存在

1. 安装问题

• 错误: "没有名为 'mcp' 的模块"
  • 运行: uv pip install mcp>=1.2.0
• 错误: "找不到 UV 命令"
  • 安装 UV: curl -LsSf https://astral.sh/uv/install.sh | sh

1. 配置

• 错误: "无法启动 MCP 服务器"
  • 验证 config.json 语法
  • 检查路径分隔符（在 Windows 上使用 \）
  • 确保 UV 在您的系统 PATH 中

贡献

1. 叉出仓库
2. 创建功能分支
3. 提交拉取请求

许可证

MIT

支持

问题：GitHub Issues