claude-flow
Verified · 2 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
agentshield-mcp
Verified · 19 days agoDetect prompt injection, jailbreak, and social-engineering attacks in LLM agents.
Install
claude mcp add agentshield-mcp -- npx -y @eigenart/[email protected]
Our take
This server is aimed at detecting prompt injection, jailbreak, and social-engineering attacks in LLM agent systems. It is relevant for teams building agent pipelines that need an explicit security screening layer. The use case is clear, but with no usage or community signals in the listing, it reads as specialized and still unproven rather than established.
Verification record
- 19 days ago
- 0
- 3 mo ago
- no
- MIT
- 53
- 0.1.6
- 2026-04-20
More in ai
browse all →tldraw
Verified · 4 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 21 days agoCodebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 16 days agoOfficial OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
mobilerun
Verified · 5 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
PraisonAI
Verified · 20 days agoAI Agents Framework with Self Reflection and MCP support