MCP Variance Log
Agentic tool that looks for statistical variations in conversation structure and logs unusual events to a SQLite database. Built using the Model Context Protocol (MCP), this system is designed to be used with Claude Desktop or other MCP-compatible clients.
Requirements
- Python ≥3.10
- MCP ≥1.2.0
- SQLite3
- UV (Python package installer and environment manager)
Quick Start
# Clone and install
git clone https://github.com/truaxki/mcp-variance-log.git
cd mcp-variance-log
uv pip install -e .
Add to Claude Desktop config (%APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"mcp-variance-log": {
"command": "uv",
"args": [
"--directory",
"C:\\Users\\username\\source\\repos\\mcp-variance-log", # Update this path
"run",
"mcp-variance-log"
]
}
}
}
Add to Claude Desktop preferences:
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
Usage
Automatic Logging Examples
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`
}
Dataframe view
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...
Text 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"}]
Detailed Installation
- Ensure Python 3.10+ and UV are installed.
Install UV using one of these methods:
# Using pip (recommended for Windows)
pip install uv
# Using installation script (Linux/MacOS)
curl -LsSf https://astral.sh/uv/install.sh | sh
- Clone and install:
git clone https://github.com/truaxki/mcp-variance-log.git
cd mcp-variance-log
uv pip install -e .
- Configure Claude Desktop:
Add to claude_desktop_config.json:
{
"mcpServers": {
"mcp-variance-log": {
"command": "uv",
"args": [
"--directory",
"PATH_TO_REPO/mcp-variance-log",
"run",
"mcp-variance-log"
]
}
}
}
Config locations:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Monitoring
log-query: Tracks conversation patterns- HIGH: Common interactions (not logged)
- MEDIUM: Unusual patterns (logged)
- LOW: Critical events (priority logged)
Query
read-logs: View logs with filteringread_query: Execute SELECT querieswrite_query: Execute INSERT/UPDATE/DELETEcreate_table: Create tableslist_tables: Show all tablesdescribe_table: Show table structure
Located at data/varlog.db relative to installation.
Schema
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
);
Troubleshooting
- Database Access
- Error: "Failed to connect to database"
- Check file permissions
- Verify path in config
- Ensure
/data directory exists
- Installation Issues
- Error: "No module named 'mcp'"
- Run:
uv pip install mcp>=1.2.0
- Error: "UV command not found"
- Install UV:
curl -LsSf https://astral.sh/uv/install.sh | sh
- Configuration
- Error: "Failed to start MCP server"
- Verify config.json syntax
- Check path separators (use \ on Windows)
- Ensure UV is in your system PATH
Contributing
- Fork the repository
- Create feature branch
- Submit pull request
License
MIT
Support
Issues: GitHub Issues