Codebase Insight MCP server

Provides deep code analysis capabilities for software repositories, enabling pattern detection, architecture understanding, and knowledge management through a FastAPI server with Qdrant vector database integration.
Back to servers
Provider
Tosin Akinosho
Release date
Mar 20, 2025
Language
Python
Package
Stats
2.7K downloads
4 stars

MCP Codebase Insight is a system designed for analyzing and understanding codebases through semantic analysis, pattern detection, and documentation management. It provides tools for developers to gain deeper insights into their code through various analysis techniques.

Installation

Install the package using pip:

pip install mcp-codebase-insight

Basic Usage

Analyzing Code

The core functionality allows you to analyze a codebase:

from mcp_codebase_insight import CodebaseAnalyzer

analyzer = CodebaseAnalyzer()
results = analyzer.analyze_code("path/to/code")

Debugging Utilities

The package includes several debugging utilities to help with troubleshooting:

from mcp_codebase_insight.utils.debug_utils import debug_trace, DebugContext, get_error_tracker

# Use debug trace decorator
@debug_trace
def my_function():
    # Your function implementation here
    pass

# Use debug context
with DebugContext("operation_name"):
    # Code to debug
    pass

# Track errors
try:
    # Potentially risky operation
    pass
except Exception as e:
    error_id = get_error_tracker().record_error(e, context={"operation": "description"})
    print(f"Error recorded with ID: {error_id}")

Testing

The package includes comprehensive testing capabilities:

# Run all tests
pytest tests/

# Run unit tests
pytest tests/unit/

# Run component tests
pytest tests/components/

# Run tests with coverage
pytest tests/ --cov=src --cov-report=term-missing

Features

Available Features

  • Core Vector Store System
  • Basic Knowledge Base
  • SSE Integration
  • Testing Framework
  • TDD and Debugging Framework

Coming Soon

  • Documentation Management System
  • Advanced Pattern Detection
  • Performance Optimization
  • Advanced Caching Strategies
  • Custom Pattern Plugins
  • Comprehensive Error Tracking System

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later