AgentsSec | AI Security (MCP/Orchestration)

🧠 Securing AI Agents & Orchestration | 🛡️MCP Security | OSS + research for safe connectors, pipelines, & multi-agent systems | #AISecurity

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

🛡️ Agents are the new attack surface.
I’m starting @AgentsSec to focus on MCP & Agent Security — securing orchestration flows, connectors & multi-agent systems.
🧵 Why this matters + what I’ll be sharing 👇

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@growing_daniel I left my faucet running by mistake and it overflowed, water seeped through roof to the ground floor. I am camping right now waiting for moisture to dry out and smell to go away.

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@araghougassian BET

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@vulturetrades options

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@vulturetrades $SPY

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@clintoptions $SPY

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

Question for Vibe Coders:
Do you read AI code before deployment? Or is it trust and don’t verify?
#vibecoding #ai

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@RhysSullivan I like the part where it explains woof wooooof in detail.

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@aakashgupta It’s good but not new. Most appsec tool provide automatic fixes through prs. The real bottleneck has always been regression testing.

[Piotr Migdal @pmigdal]

Claude can code, but can it read machine code?

We gave AI agents access to Ghidra (a decompiler by the NSA) and tasked them with finding hidden backdoors in servers - working solely from binaries, without any access to source code.

See our BinaryAudit: https://t.co/VPNk5ChPfH

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@HumansNoContext I thought it was just me

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

What’s the best ai model for threat modeling?

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@intigriti Mcp security

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@wholemars You got the whole mars catalog

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

This is just the beginning 🚀

If you’re working on AI agents, orchestration or MCP, follow @AgentsSec.
Let’s secure the future of AI together.
#AISecurity #MCP #LLMSecOps

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

🛡️ Agents are the new attack surface.
I’m starting @AgentsSec to focus on MCP & Agent Security — securing orchestration flows, connectors & multi-agent systems.
🧵 Why this matters + what I’ll be sharing 👇

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

My mission:
Help enterprises secure AI orchestration flows by building tools, sharing research & raising awareness around MCP & Agent Security.

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@vaespc I had this for over a year. It wouldn’t just go away. I had seen so many doctors. Finally a very smart doctor fixed it.

[AgentsSec | AI Security (MCP/Orchestration) @AgentsSec]

@aaditsh AI