Loading video...

Video Failed to Load

Go Home

Write 100x better code using AI (for free!) Install the Codacy extension (VSCode, Cursor, WindSurf). This will install an MCP Server locally on your computer. Your coding copilot will use this server with the Codacy CLI to check every line of code it generates. The way this works is...

63,219 views • 11 months ago •via X (Twitter)

10 Comments

Chris Mullins's profile picture
Chris Mullins11 months ago

@codacy How does it compare to @coderabbitai ? I have been super impressed with it...

Thack's profile picture
Thack11 months ago

@codacy Sponsored post.

Samarth's profile picture
Samarth11 months ago

@codacy Which MCP servers do you use on Cursor given that 53 tools is all it can take?

Excel For Freelancers's profile picture
Excel For Freelancers11 months ago

@codacy This is game-changing. AI writes the code, checks itself, and fixes it too? Wild how fast ‘just write it and pray it compiles’ is becoming ancient history.

Himanshu Kumar's profile picture
Himanshu Kumar11 months ago

@codacy Local MCP server boosts AI code quality.

Shanon Faneyte's profile picture
Shanon Faneyte11 months ago

@codacy Great information and it seems easy to master and use. Thanks for sharing, Santiago.

Farhan's profile picture
Farhan11 months ago

@codacy The combo of AI + MCP checks = no more sleepless nights over a missing semicolon. Sold.

Cristian Emeritus🍸🪽 | 🇦🇷 + 🇮🇹 + 🇮🇱's profile picture
Cristian Emeritus🍸🪽 | 🇦🇷 + 🇮🇹 + 🇮🇱11 months ago

@codacy I'll try it out!

Ravi Bopara's profile picture
Ravi Bopara11 months ago

@codacy Interesting, i will try this coming weekend!

Saarthak's profile picture
Saarthak11 months ago

@codacy Does this also work with Replit?

Related Videos

8 rules to improve your AI coding agent. All of these rules work with Claude Code, Cursor, VS Code, and with most programming languages. Automating these rules will 10x the code quality and security produced by your AI coding agents. 1. Dependency checks - Prevent your agent from suggesting insecure libraries based on outdated training data. 2. Secret exposure - Auto-fix the use of hardcoded credentials introduced by your coding agent. 3. File and function size - Automatically refactor any files or functions that exceed a reasonable length. 4. Complexity and parameter limits - Simplify overly complex code written by the agent. 5. SQL Injection - Auto-fix all database interactions with unsanitized user input. 6. Unused variables and imports - Detect and remove dead code. 7. Detect invisible unicode characters in AI rules files - Remove zero-width spaces, direction overrides, and other invisible characters that can hide malicious behavior. 8. Insecure OpenAI API usage - Enforce use of secure OpenAI endpoints, proper authentication, and context isolation Here is how you can automate this: Install the Codacy extension. This will give you access to a CLI for local scanning and an MCP server for agent communication. From here on out, every time you need to generate some code: 1. Your agent will write the code 2. It will then call Codacy's CLI to check it 3. It will find any issues in real time 4. Your coding agent will fix the issues 5. When the code passes all checks, you are done Level of effort on your side: literally zero! Code quality and security because of this: 100x better! Here is the link to download the extension for your IDE: Thanks to the Codacy team for collaborating with me on this post.

Santiago

48,469 views • 7 months ago

SonarQube has been catching my bugs and security issues for years. The only friction was having to leave Cursor or Windsurf to view the results. Their new MCP Server fixes that by bringing verification directly into the coding environment 🔥 This is actually perfect timing 🧵 ↓ Because we write more code than ever thanks to AI, yet productivity still doesn’t keep up. Google’s 2025 DORA Report shows the tension: → AI usage +90% → Bugs +9% → Review time +91% → PR size +154% (report here: The problem isn’t generating code. It’s verifying it quickly and reliably. And this is what SonarQube's new MCP Server brings instantly: - Live scanning → trigger SonarQube checks inside Cursor, Windsurf, Claude Code… basically any MCP-compatible IDE - Immediate surfacing → security, reliability, and maintainability issues in seconds - Smooth UI handoff → jump to the dashboard only when you need the full picture - AI-native workflow → Sonar’s long-standing rule engine integrated into your daily loop Why it’s great: • Removes constant tab-switching • Faster write → check → fix cycles • Lets the IDE handle speed while SonarQube handles structure • Feels like code quality finally meets AI-native development Setup is super simple: → Enable SonarQube's MCP Server in Cursor → Add your SonarQube instance → Open your repo → Run the scan directly inside the IDE I then pointed it to a JS component I’m building in Streamlit (psst, it’s called Streamlit ChartJS ;)) → Immediate results: security flags, reliability concerns, maintainability smells, and dependency risks ✅ Then I prompted: "Show me the full breakdown." → Cursor opens the SonarQube UI with rule details, severities, fix guidance, and project-wide quality signals! Exactly on point.

Charly Wargnier

22,702 views • 5 months ago