jnMetaCode/shellward

Overview

Shellward is a security middleware for AI agents. It provides an 8-layer defense system with data loss prevention (DLP) and prompt injection detection. The tool includes an SDK and an MCP server for integration with Claude Code, Cursor, LangChain, Hermes Agent, and similar platforms.

Best for

Best for
Developers building AI agent systems that need a drop-in security and DLP layer

Use cases

• Securing AI agent interactions from prompt injection attacks
• Enforcing data loss prevention policies on agent data flows
• Adding a security layer to custom AI agent pipelines using the SDK

How to use

Install

npx shellward scan

Tools exposed

• check_command
• check_injection
• scan_data
• check_path
• check_tool
• check_response
• scan_mcp_tool
• security_status
• compliance_check
• SHELLWARD_MODE
• SHELLWARD_LOCALE
• SHELLWARD_THRESHOLD
• SHELLWARD_BASELINE_PATH

Tested with

Claude Desktop, Claude Code, Cursor, ChatGPT

Notes

Shellward is a security middleware for AI agents. It provides an 8-layer defense system with data loss prevention (DLP) and prompt injection detection. The tool includes an SDK and an MCP server for integration with Claude Code, Cursor, LangChain, Hermes Agent, and similar platforms.

101 stars on GitHub. Last updated 2026-05-18. Licensed Apache-2.0.

Use cases

• Securing AI agent interactions from prompt injection attacks
• Enforcing data loss prevention policies on agent data flows
• Adding a security layer to custom AI agent pipelines using the SDK

Pros

• Zero external dependencies reduces integration risk
• Multi-layer defense offers broad coverage for common AI agent attacks
• Compatible with multiple popular AI agent frameworks and tools

Cons

• Low GitHub star count (101) suggests limited community adoption
• Vendor listed as ‘Various’ may indicate unclear long-term maintenance
• MCP server configuration may add overhead for simple use cases

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.