claude-flow
Verified · 17 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
agent-immune
Verified · 6 days agoAI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
Install
claude mcp add agent-immune -- uvx agent-immune
Our take
This is an AI-security-oriented server focused on prompt-injection detection, output scanning, prompt hardening, and related agent-safety controls. It is for teams building LLM agents that need defensive layers around prompts, memory, and generated outputs. The positioning matches a real need, but security claims deserve extra scrutiny, and with no usage signal here it should be treated as an experimental control layer rather than a trusted security boundary.
Verification record
- 6 days ago
- 0
- 2 mo ago
- no
- Apache-2.0
- 2026-04-07
More in ai
browse all →tldraw
Verified · 18 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 8 days agoCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · todayOfficial OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.
mobilerun
Verified · 20 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
PraisonAI
Verified · 7 days agoAI Agents Framework with Self Reflection and MCP support