# agentshield-mcp MCP server

Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-dl-eigenart-agentshield-mcp
- Repository: https://github.com/dl-eigenart/agentshield-platform
- Website: https://agentshield.pro

## Install
- Command: `npx -y @eigenart/agentshield-mcp`
- Auth: Auth required by registry metadata

## Setup notes
- Package: Npm @eigenart/agentshield-mcp v0.1.3
- Environment variable: AGENTSHIELD_API_KEY (required; secret)
- The upstream registry signals required auth or secrets.

## Tools
Not captured

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.dl-eigenart
- Version: 0.1.3
- Runtime: Npm
- Transports: STDIO
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Apr 20, 2026
- Source: https://registry.modelcontextprotocol.io