SQLite

by emiryasar

39 stars

456 downloads

Not rated

GitHub

About

Provides a lightweight SQLite-based storage solution, supporting basic CRUD operations for small to medium-scale projects.

Details

Author: emiryasar
Repository: emiryasar/mcp_code_analyzer
GitHub stars: 39
Downloads: 456
License: MIT License
Categories: Productivity, Design, Developer Tools, File Management, Project Management, Frontend, Database, Infrastructure

- Project analysis: structure (XML tree), statistics, technology, code structure
- Code analysis: imports, file analysis, reference finding
- File operations with automatic dated backup creation
- Code modifier for line-by-line code changes (known issues)
- Supports multiple project paths with no limit on paths or files
- Integrates with Claude Desktop via the Model Context Protocol

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name SQLite

Command (node, npx, python, etc.) python
Arguments
- Argument 1 -m
- Argument 2 mcp_code_analyzer
- Argument 3 --analyze-paths
- Argument 4 C:\Projects\path1
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

JSON

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

From the repository

1. Access Claude Desktop config:

   Win + R → %AppData%\Claude\

2. Create/edit claude_desktop_config.json:

   {

     "globalShortcut": "Ctrl+Space",

     "mcpServers": {

       "code-analyzer": {

         "command": "python",

         "args": [

           "-m",

           "mcp_code_analyzer",

           "--analyze-paths",

           "C:\\Projects\\path1"

         ],

         "type": "module"

       }

     }

   }

pip install -e .
```

- Multiple project paths can be specified in configuration
- Additional paths or files can be analyzed via chat messages
- No limit on number of analyzable paths/files

`analyze_project_structure`

Analyzes the structure of the project and returns it in XML tree format.

`analyze_project_statistics`

Provides statistical analysis of the project.

`analyze_project_technology`

Analyzes the technologies used in the project.

`analyze_code_structure`

Analyzes the structure of the code within the project.

`analyze_imports`

Analyzes the import statements in the code.

`analyze_file`

Analyzes a specific file within the project.

`find_references`

Finds references to specific elements in the code.

`file_operations`

Performs various file operations, including potential modifications.

`version_control`

Creates dated backups of files for version control.

`code_modifier`

Modifies code line by line, but currently has significant issues.

`check_syntax`

Checks the syntax of the code for any errors.

`find_code_patterns`

Identifies patterns in the code.

`find_pattern_usages`

Finds where specific patterns are used in the code.

`search_content`

Searches for specific content within the code.

`search_files`

Searches through files for specific terms or patterns.

`validate_code`

Validates the code to ensure it meets certain standards.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "sqlite": {
            "cwd": "C:\\Projects\\path1",
            "env": {},
            "args": [
                "-m",
                "mcp_code_analyzer",
                "--analyze-paths",
                "C:\\Projects\\path1"
            ],
            "command": "python"
        }
    }
}

Linux

{
    "cwd": "C:\\Projects\\path1",
    "env": [],
    "args": [
        "-m",
        "mcp_code_analyzer",
        "--analyze-paths",
        "C:\\Projects\\path1"
    ],
    "command": "python"
}

Macos

{
    "cwd": "C:\\Projects\\path1",
    "env": [],
    "args": [
        "-m",
        "mcp_code_analyzer",
        "--analyze-paths",
        "C:\\Projects\\path1"
    ],
    "command": "python"
}

Windows

{
    "cwd": "C:\\Projects\\path1",
    "env": [],
    "args": [
        "-m",
        "mcp_code_analyzer",
        "--analyze-paths",
        "C:\\Projects\\path1"
    ],
    "command": "python"
}

MCP Code Analyzer

The main purpose of the MCP tool is to adapt changes to the project intelligently. For instance, when a code modification or structural adjustment is needed, it aims to ensure that other related usages are also updated accordingly.

Currently, the project has a lot of bugs, and the tools are not functioning as expected sometimes. Due to work commitments,
I can’t dedicate much time to it, but I’ll try to fix the issues and bring it to a working state whenever I find the time.

⚠️ WARNING: BACKUP RECOMMENDED
This tool performs file operations that could potentially modify or delete files. Always backup your codebase before using any modification features.

Overview

The Model Context Protocol (MCP) Code Analyzer is a comprehensive code analysis and management tool that integrates with Claude Desktop. It analyzes code at both project and file levels, providing insights for needed changes and project understanding.

Prerequisites

- Python 3.10 or later - Windows (Linux/MacOS support not yet tested)

Installation

# Clone the repository
git clone https://github.com/[your-username]/mcp-code-analyzer.git
cd mcp-code-analyzer
Install dependencies and package
pip install -e .

Claude Desktop Integration

Configuration

1. Access Claude Desktop config:

   Win + R → %AppData%\Claude\

2. Create/edit claude_desktop_config.json:

   {
     "globalShortcut": "Ctrl+Space",
     "mcpServers": {
       "code-analyzer": {
         "command": "python",
         "args": [
           "-m",
           "mcp_code_analyzer",
           "--analyze-paths",
           "C:\\Projects\\path1"
         ],
         "type": "module"
       }
     }
   }

Path Configuration

- Multiple project paths can be specified in configuration - Additional paths or files can be analyzed via chat messages - No limit on number of analyzable paths/files

🛠️ Tools and Status

Working Tools

- ✅ Project Analysis - analyze_project_structure (XML tree format) - analyze_project_statistics - analyze_project_technology - analyze_code_structure

- ✅ Code Analysis
- analyze_imports
- analyze_file
- find_references

- ⚠️🔄 File Operations (Always backup before use)
- file_operations
- version_control (Creates dated backups)
-
- ⚠️🔄 Code Modify (Always backup before use)
- code_modifier (Performs modifying code line by line)(Currently has big issues)

Testing Phase

- 🔄 check_syntax
- 🔄 find_code_patterns
- 🔄 find_pattern_usages
- 🔄 search_content
- 🔄 search_files
- 🔄 validate_code

Known Issues

1. Chat context limitations may interrupt large file modifications 2. AI-generated documentation comments can affect code operation in large files

Demo Video

Watch demonstration of MCP tool using with building Mario game:

Mario Game with Claude | MCP Code Analyzer Tool Demonstration

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

analyze_project_structure

analyze_project_statistics

analyze_project_technology

analyze_code_structure

analyze_imports

analyze_file

find_references

file_operations

version_control

code_modifier

check_syntax

find_code_patterns

find_pattern_usages

search_content

search_files

validate_code

Claude Desktop / Cursor

Linux

Macos

Windows

MCP Code Analyzer

Overview

Prerequisites

Installation

Install dependencies and package

Claude Desktop Integration

Configuration

Path Configuration

🛠️ Tools and Status

Working Tools

Testing Phase

Known Issues

Demo Video

Install

More like this

Time

Sentry

Github

Git

GitLab

Context 7

`analyze_project_structure`

`analyze_project_statistics`

`analyze_project_technology`

`analyze_code_structure`

`analyze_imports`

`analyze_file`

`find_references`

`file_operations`

`version_control`

`code_modifier`

`check_syntax`

`find_code_patterns`

`find_pattern_usages`

`search_content`

`search_files`

`validate_code`