claude-flow
Verified · 3 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
AI Firewall MCP
Verified · 22 days agoMulti-agent LLM security layer detecting prompt injection and jailbreaks.
Install
claude mcp add ai-firewall-mcp -- uvx ai-firewall-mcp
Our take
This server focuses on LLM security, specifically prompt-injection and jailbreak detection across multi-agent setups. It is for teams operating agent systems that need an extra inspection layer before model actions or tool calls proceed. Security tooling is valuable here, but with minimal adoption signals in the listing, effectiveness and false-positive rates would need independent verification.
Verification record
- 22 days ago
- 0
- 2 mo ago
- no
- MIT
- 2026-06-09
More in ai
browse all →tldraw
Verified · 5 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 22 days agoCodebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 17 days agoOfficial OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
mobilerun
Verified · 6 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
PraisonAI
Verified · 21 days agoAI Agents Framework with Self Reflection and MCP support