Code Analysis
About
Integrates code analysis using a Neo4j graph database to enable structural insights, quality metrics, and natural language querying of codebases.
Details
- Author
- davidvc
- Repository
- davidvc/code-mcp
- GitHub stars
- 10
- License
- Apache License 2.0
- Categories
- Developer Tools, Design, Workplace, File Management, AI, Search, Database, Security, Knowledge Base
- Tags
- #analytics
Jump to
- Code Structure Analysis
- Component and module relationships
- Class hierarchies and dependencies
- Method complexity and relationships
- File organization and imports
- Code Quality Metrics
- Cyclomatic complexity
- Coupling and cohesion metrics
- Code duplication detection
- Test coverage analysis
- Documentation Analysis
- Markdown file parsing
- Documentation quality metrics
- Documentation coverage analysis
- Automated documentation updates
- Natural Language Queries
- Ask questions about code structure
- Get high-level architectural overviews
- Identify potential code issues
- Find relevant code examples
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
Code AnalysisCommand (node, npx, python, etc.)npxArguments-
Argument 1
-y -
Argument 2
@highlight/mcp-server
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
See CONTRIBUTING.md for development setup instructions.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"code analysis": {
"env": {},
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
}
}Linux
{
"env": [],
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}Macos
{
"env": [],
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}Windows
{
"env": [],
"args": [
"/c",
"npx",
"-y",
"@highlight/mcp-server"
],
"command": "cmd"
}Code Analysis MCP Plugin
A Model Context Protocol (MCP) plugin that enables AI assistants like Cline and Claude to perform sophisticated code analysis and answer questions about codebases.
Overview
This plugin provides AI assistants with direct access to codebase analysis capabilities through a Neo4j graph database, enabling them to:
- Analyze code structure and relationships
- Calculate code quality metrics
- Extract documentation and context
- Answer high-level questions about the codebase
Features
- Code Structure Analysis
- Component and module relationships
- Class hierarchies and dependencies
- Method complexity and relationships
- File organization and imports
- Code Quality Metrics
- Cyclomatic complexity
- Coupling and cohesion metrics
- Code duplication detection
- Test coverage analysis
- Documentation Analysis
- Markdown file parsing
- Documentation quality metrics
- Documentation coverage analysis
- Automated documentation updates
- Natural Language Queries
- Ask questions about code structure
- Get high-level architectural overviews
- Identify potential code issues
- Find relevant code examples
Example Queries
The plugin can answer questions like:
- "Please summarize the key features and functionality of this codebase"
- "Write a high level design document for this codebase, using object and sequence diagrams where useful"
- "Write a summary of the key components of this codebase, with a paragraph or two for each component"
- "What are some of the more problematic files, applying SOLID and clean coding principles"
Architecture
The plugin uses:
- Neo4j graph database for storing code structure and relationships
- Language-specific parsers for code analysis
- MCP interface for AI assistant integration
- Advanced metrics calculation for code quality analysis
Getting Started
See CONTRIBUTING.md for development setup instructions.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
