- LISTING
- TRIAGE
- REPORTS
- HUMAN
Short answer
How can I use AI to find security holes in my code?
Your AI uses the Codacy MCP to pull a list of security issues from specific repositories. You get a targeted report of critical vulnerabilities to review immediately.
The results of your audit.
Where your security data lands.
The agent turns raw security data into organized lists.
LISTING
Vulnerability lists
The AI pulls all active security issues from the repo. You get a clean list of what's broken.
TRIAGE
Criticality sorting
The agent identifies which issues are high-risk. This helps you focus on the most dangerous bugs first.
REPORTS
Summary findings
Your AI summarizes the state of your repository security. It turns complex scan data into plain English.
HUMAN
Manual fixes
The AI identifies the problems, but you still have to write the code to fix them. You decide which patches to apply.
The workflow
What your AI does when the request arrives.
The agent acts as a bridge between your chat interface and your code security data.
Access the repo
The agent connects to the target repository to prepare for the scan.
search_repository_issuesIdentify vulnerabilities
The AI looks through the repository issues to find security-related flags.
search_repository_issuesFilter by severity
The agent narrows down the results to show only the critical or high-priority threats.
search_repository_issuesPresent findings
Your AI organizes the discovered issues into a readable format for your review.
search_repository_issues
Try it
Copy these to start.
Use these prompts to trigger the security audit.
Starting points
Replace the repository names with your actual project names.
Codacy Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_KbaaZYN1bP8SnLjmfwP5o8lSuAGcVbr6otbUJbbw/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Codacy capabilities are ready to use.
{
"mcpServers": {
"codacy-mcp": {
"url": "https://edge.vinkius.com/vk_preview_KbaaZYN1bP8SnLjmfwP5o8lSuAGcVbr6otbUJbbw/mcp"
}
}
}Search for all critical security issues in the 'auth-service' repository.
List the top security vulnerabilities found in 'frontend-app'.
Are there any high-severity security issues in the 'payment-gateway' repo?
Summarize the security status for the 'data-processor' repository.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Codacy once, then ask.
Just link your account with one click. Your credentials stay encrypted, and you can start auditing immediately.
Connect Codacy to your AIFAQ
How this task behaves.
- 01
Can the AI fix the security vulnerabilities for me?
No. The AI identifies and lists the issues, but you must manually implement the code fixes.
- 02
Does the AI delete any issues in Codacy?
No. The AI only reads issue data. It cannot modify, delete, or close issues in your repository.
- 03
Can I audit any repository?
You can audit any repository that you have already connected to Codacy.
- 04
Will the AI scan my entire codebase?
The AI scans the issues reported by Codacy for the specific repository you name.
- 05
How does the AI know which issues are critical?
The AI reads the severity levels assigned to the issues within the repository data.
More questions about Codacy? The Connector page answers them. See everything the Codacy Connector can do
Connect Codacy to Claude, Cursor, ChatGPT & more
