Mcp Test
Create and interact with an SQLite database derived from compressed log files, enabling efficient analysis of log data through structured queries. Gain insights into application behavior and performance seamlessly using the Model Context Protocol.
Author
direkt
No License
Quick Info
Tools 1
Last Updated 8/3/2025
Actions
Tags
databases sqlite database secure database databases secure database access
This project provides tools to create an SQLite database from compressed log files and interact with it using the Model Context Protocol (MCP) SQLite server.
python3 -m venv venv
source venv/bin/activate
pip3 install -r requirements.txt
Place log files in the folder as .gz files, then run:
python3 create_log_db.py
To configure the MCP SQLite server in Cursor-
- Cursor Settings
- MCP
- Add New MCP Server
- Name
SQLlite - Set the type to
command - Put this in the command box
npx -y @smithery/cli@latest run mcp-server-sqlite-npx --config "{\"databasePath\":\"/path/to/thedatbase/logs.db\"}"
create_log_db.py: Script to extract and parse log files into an SQLite databasequery_logs.py: Script to directly query the SQLite databaselogs.db: SQLite database containing parsed log data
The database contains the following tables:
logs Table
id: Unique identifier for each log entrytimestamp: Timestamp of the log entrythread: Thread that generated the loglevel: Log level (INFO, WARN, ERROR, DEBUG)module: Module that generated the logmessage: Log message contentsource_file: Source log fileraw_log: Raw log entry
stack_traces Table
id: Unique identifier for each stack tracelog_id: Reference to the log entry this stack trace belongs tostack_trace: Full stack trace text
parsing_errors Table
id: Unique identifier for each parsing errorline: The line that couldn't be parsedsource_file: Source log fileerror_message: Error message explaining why parsing failedtimestamp: When the parsing error occurred
You can query the database directly using the query_logs.py script: