jnMetaCode/shellward
by Various
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP server for Claude Code, Cursor, LangChain, Hermes Agent & mo
MCP
jnMetaCode/shellward
Added 1 June 2026
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
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.
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
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Claude Code
Anthropic
Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.
Cursor
Anysphere
The AI-first code editor. Tab to autocomplete, Composer to multi-file refactor, Agents for the long-running stuff.
LangChain
Community
The agent engineering platform.