Registro de varianza de MCP
Herramienta de Agentic que busca variaciones estadísticas en la estructura de las conversaciones y registra eventos inusuales en una base de datos SQLite. Desarrollado con el Protocolo de Contexto de Modelo (MCP), este sistema está diseñado para usarse con Claude Desktop u otros clientes compatibles con MCP.
Requisitos
- Python ≥3.10
- MCP ≥1.2.0
- SQLite3
- UV (instalador de paquetes de Python y administrador de entorno)
Inicio rápido
# Clone and install
git clone https://github.com/truaxki/mcp-variance-log.git
cd mcp-variance-log
uv pip install -e .
Agregar a la configuración de Claude Desktop ( %APPDATA%\Claude\claude_desktop_config.json en Windows):
{
"mcpServers": {
"mcp-variance-log": {
"command": "uv",
"args": [
"--directory",
"C:\\Users\\username\\source\\repos\\mcp-variance-log", # Update this path
"run",
"mcp-variance-log"
]
}
}
}
Agregar a las preferencias de Claude Desktop:
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
Uso
Ejemplos de registro automático
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`
}
Vista de marco de datos
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...
Texto 2 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"}]
Instalación detallada
- Asegúrese de que Python 3.10+ y UV estén instalados.
Instale UV utilizando uno de estos métodos:
# Using pip (recommended for Windows)
pip install uv
# Using installation script (Linux/MacOS)
curl -LsSf https://astral.sh/uv/install.sh | sh
- Clonar e instalar:
git clone https://github.com/truaxki/mcp-variance-log.git
cd mcp-variance-log
uv pip install -e .
- Configurar Claude Desktop:
Agregar a claude_desktop_config.json :
{
"mcpServers": {
"mcp-variance-log": {
"command": "uv",
"args": [
"--directory",
"PATH_TO_REPO/mcp-variance-log",
"run",
"mcp-variance-log"
]
}
}
}
Ubicaciones de configuración:
- Ventanas:
%APPDATA%\Claude\claude_desktop_config.json - MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Herramientas
Escucha
log-query : rastrea patrones de conversación- ALTO: Interacciones comunes (no registradas)
- MEDIO: Patrones inusuales (registrados)
- BAJO: Eventos críticos (prioridad registrada)
Consulta
read-logs : Ver registros con filtradoread_query : Ejecutar consultas SELECTwrite_query : Ejecutar INSERTAR/ACTUALIZAR/ELIMINARcreate_table : Crear tablaslist_tables : Mostrar todas las tablasdescribe_table : Mostrar la estructura de la tabla
Ubicado en data/varlog.db relativo a la instalación.
Esquema
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
);
Solución de problemas
- Acceso a bases de datos
- Error: "Error al conectar con la base de datos"
- Comprobar permisos de archivos
- Verificar ruta en la configuración
- Asegúrese de que exista el directorio
/data
- Problemas de instalación
- Error: "No existe ningún módulo llamado 'mcp'"
- Ejecutar:
uv pip install mcp>=1.2.0
- Error: "Comando UV no encontrado"
- Instalar UV:
curl -LsSf https://astral.sh/uv/install.sh | sh
- Configuración
- Error: "No se pudo iniciar el servidor MCP"
- Verificar la sintaxis de config.json
- Verifique los separadores de ruta (use \ en Windows)
- Asegúrese de que la luz UV esté en la RUTA de su sistema
Contribuyendo
- Bifurcar el repositorio
- Crear rama de características
- Enviar solicitud de extracción
Licencia
Instituto Tecnológico de Massachusetts (MIT)
Apoyo
Problemas: Problemas de GitHub