ShellWard
Security middleware that protects agents from prompt injection, data exfiltration, and dangerous command execution with 8-layer de
ShellWard intercepts tool calls at runtime to enforce security guardrails using an 8-layer defense architecture. It provides DLP-style data flow control that blocks outbound data transmission when sensitive information was recently accessed, prompt injection detection with 32 rules covering English and Chinese, dangerous command blocking, PII scanning, and session monitoring. Works as a standalone SDK or MCP server with zero dependencies across Claude Desktop, Cursor, and other MCP-compatible clients.
Source
Repository: https://github.com/jnmetacode/shellward
Maintain ShellWard?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/jnmetacode-shellward?ref=badge) Related mcp
Package Version Checker Get package version data from npm and PyPI registries to assist with dependency management.
n8n Bridges Claude with n8n automation workflows, enabling direct creation, execution, and management of workflows, credentials, and e
Socket Security Integrates with Socket's dependency security API to analyze npm and PyPI packages, returning detailed security and quality metrics
Python Interpreter Provides a secure Python execution environment with isolated working directories, enabling code execution, file operations, and pa
Code Pathfinder AI-native static code analysis with call graphs, data flow tracing, type inference, and symbol search for Python and Go.
VirusTotal This VirusTotal MCP server enables AI assistants to programmatically access VirusTotal's threat intelligence for security analysis