AgentScan checks exposed AI agent endpoints in one command
AgentScan is an for finding exposed AI-related endpoints on the internet or inside a private network. A normal port scanner may only show that a web service is open, but AgentScan checks whether that service is an MCP server, an , or an open LLM interface. Its results can include available tools, agent abilities, model lists, and whether is required.
For MCP, it checks Streamable HTTP, older HTTP+SSE setups, tool lists, resource lists, prompt lists, state, and honeypot signs. For A2A, it checks Agent Card data, skills, interfaces, und JSON-RPC access, and leaked private network addresses. For open LLM interfaces, it recognizes tools such as Ollama, vLLM, SGLang, TGI, llama.cpp, Xinference, LiteLLM, FastChat, LocalAI, LM Studio, and LMDeploy.
It can scan domains, , private network ranges, or a prepared list of open host:port targets, and it can save results as JSON files. Its stated use is authorized company security work, not scanning targets without permission.
Key points
- Scans , s, and open LLM interfaces in one command.
- Reports available tools, agent abilities, model lists, and state.
- Recognizes LLM stacks such as Ollama, vLLM, LiteLLM, and LocalAI.
- Can scan a domain, IP address, private network range, or known host:port list.
- Can write JSON results for later review or security tracking.