# Code security

The Apiiro Guardian Agent MCP server connects AI programming assistants with the Apiiro security analysis platform, providing real - time code security analysis, risk queries, scan triggering, and security management functions through the MCP protocol.

ClaudeSmalltalk is a project that connects Claude Desktop to a running Smalltalk programming environment. It provides 14 tools such as code evaluation, class browsing, and method definition through the MCP protocol, supports local or cloud LLM drivers, and ensures that the code is secure and does not leave the local machine.

A code security firewall MCP service based on structural similarity. It intercepts malicious code patterns before code execution by parsing the code structure and comparing it with the blacklist of dangerous patterns.

Memoria is an MCP server that reveals hidden dependencies between code files by analyzing Git history, preventing AI from breaking functionality when refactoring code. It runs entirely locally without uploading code to the cloud, ensuring the security of code modifications by detecting coupling relationships, risk scores, and outdated dependencies between files.

Ranex Community Edition is an AI-native Python governance framework that ensures the production readiness of AI-generated code through functions such as state machine verification, security scanning, and architecture checking.