git clone https://github.com/saiprashanths/code-analysis-mcp.git
cd code-analysis-mcp

{
  "mcpServers": {
    "code-analysis": {
      "command": "uv",
      "args": [
        "--directory",
        "/PATH/TO/YOUR/REPO",
        "run",
        "code_analysis.py"
      ]
    }
  }
}

You: How does the transaction processing work in this system?

Claude: Let me analyze the data flow for transactions. 
Looking at the codebase, I can see that transaction processing happens through several key components:

1. Raw transaction data is captured in the `TransactionEvent` model with fields for:
   - Payment status
   - Amount
   - Fee calculations
   - Processing timestamps

2. This data is then processed through the PaymentSummary model, which:
   - Validates payment provider responses
   - Calculates processing fees
   - Records transaction status

Would you like me to explain any part of this in more detail?

You: What are the key database tables involved?

Claude: The main tables in the transaction processing pipeline are:

1. transaction_events: Stores raw payment events
2. payment_summary: Processed transaction records
3. payment_providers: Provider configuration
4. merchant_accounts: Account-specific settings

Let me know if you'd like to see the schema for any of these tables!

initialize_repository("/path/to/repo")
# Output: Successfully initialized code repository at: /path/to/repo

get_repo_info()
# Output:
# Code Repository Information:
# Path: /path/to/repo
# Exists: True
# Is Directory: True
# Found .gitignore file

get_repo_structure(depth=2)
# Output:
# 📁 src/
#   📁 api/
#     📄 routes.py
#     📄 models.py
#   📁 utils/
#     📄 helpers.py
#   📄 main.py

read_file("src/api/models.py")
# Output:
# File: src/api/models.py
# Language: python
# Size: 2.3 KB
# 
# [File contents...]