A → LLM
Agent to LLM
- Virtual keys per agent
- Prompt guards and redaction
- Token and budget limits
Personal blog · security notes and projects
Secure every hop your AI agents make.
Notes and working projects on securing agentic AI: identity, policy and audit on agent-to-agent, agent-to-LLM and agent-to-tool traffic. I build small proofs of concept in my own time and share the code and what I learned.
coverage
Three paths, one policy point
A → MCP
Agent to tools (MCP)
- Authenticated tool access
- Per-identity tool scoping
- Guardrails on tool calls and responses
- Audit trail
A → A2A
Agent to agent (A2A)
- An identity for every agent
- mTLS
- Authorization on each hop
- End-to-end tracing
projects
Latest project
PublishedPROJECT-001
Securing agent traffic with an open-source agentic gateway
I put agentgateway in front of an LLM and an MCP tool server on kind and walked it through the six NIST CSF functions, with a script that proves each control.
Read the project →notes
Latest notes
feedback
Found a mistake, have an idea, or want to talk about agentic security? Open an issue on GitHub or get in touch.