roo-logger
by annenpolka·★ 24·Score 40
An MCP server that automatically logs AI coding assistant activities like command executions and code generation.
Overview
Roo Activity Logger is a comprehensive MCP server designed to capture and store AI coding assistant activities in JSON format. It supports various activity types including command executions, code generation, file operations, errors, decisions, and conversations. The server provides tools for recording activities with detailed metadata such as intentions, context, and hierarchical relationships between tasks. Logs are saved as date-based JSON files, making them easily searchable and analyzable for context restoration.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose this when you need to track and analyze AI coding assistant activities for productivity analysis, context restoration, or documentation purposes.
When NOT to choose this
Avoid if you need real-time monitoring or advanced analytics capabilities, as this server only provides basic JSON logging and search functionality.
Tools this server exposes
3 tools extracted from the READMElog_activityRecord an activity with details, intention, and context
get_log_filesList saved log files recursively
search_logsSearch saved logs with various filters
Comparable tools
Installation
Installation
Via npx (Recommended)
Add the following to your Cline, Roo-Code, or Claude Code configuration:
{
"mcpServers": {
"roo-activity-logger": {
"command": "npx",
"args": ["-y", "github:annenpolka/roo-logger"],
"env": {},
"disabled": false
}
}
}Local Development
git clone https://github.com/annenpolka/roo-logger.git
cd roo-logger
npm install
npm run buildThen configure to use the local build:
{
"mcpServers": {
"roo-activity-logger": {
"command": "node",
"args": ["/path/to/your/local/roo-logger/dist/index.js"],
"env": {},
"disabled": false
}
}
}FAQ
- What activity types does the logger support?
- The logger supports command_execution, code_generation, file_operation, error_encountered, decision_made, and conversation activity types.
- How are logs stored and organized?
- Logs are saved as date-based JSON files in a specified directory. Each log contains metadata like timestamp, type, summary, details, intention, context, and parent/related IDs for hierarchical organization.
Compare roo-logger with
Last updated · Auto-generated from public README + GitHub signals.