analyze_project_structureLABSCO SUMMARY
One call for a first pass over a repository you have not read.
The orchestrator is the useful part: instead of choosing which analysis to run on unfamiliar code, you get structure, duplication and configuration together, ordered by what to deal with first.
What it is
A Python MCP server that analyses a codebase on disk: project structure and architecture, duplicate code across languages, microservices patterns and configuration. One orchestrator tool runs the whole set in order and returns a prioritised plan with a health score.
What you get
- Project organisation and architecture detected
- Duplicate code found across several languages at once
- Microservices patterns validated
- Configuration management analysed
- A comprehensive improvement report with actionable items
- One call that runs every analysis in order and returns a health score and a roadmap
Requirements
Python with the mcp package, and the path to the project you want analysed. It reads local directories and keeps its analysis history locally; there is no account and no key.
Setup effort
Build from source — git clone https://github.com/liadgez/codebase-optimizer-mcp.git
USE CASES
01
Getting oriented in a codebase you just inherited
Run the complete analysis for a health score and a roadmap, then read the structure detail behind it.
02
Finding the copy-paste before you refactor
Run duplicate detection across the languages in the repository, not one at a time.
03
Checking a split into services holds up
Validate the microservices patterns against the structure the repository actually has.
04
Cleaning up configuration that has drifted
Analyse how configuration is managed across the project and where it disagrees with itself.
05
Writing up what needs doing for somebody else
Generate the improvement report, so the handover is a list of actions rather than an opinion.
6 tools
Listed in project docs. Your client may show a different list.
detect_code_duplicatesvalidate_microservices_architectureoptimize_configurationsgenerate_improvement_reportrun_complete_project_analysisBEFORE YOU INSTALL
What to know first
Tools you get
6 tools named in the project's documentation.
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/liadgez/codebase-optimizer-mcp.git
cd codebase-optimizer-mcp
pip install mcpMCP Clients
Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"codebase-optimizer": {
"command": "python",
"args": [
"<YOUR_PATH_TO_CODEBASE_OPTIMIZER_MCP>/server.py"
],
"env": {
"PYTHONPATH": "<YOUR_PATH_TO_CODEBASE_OPTIMIZER_MCP>"
}
}
}
}
