Research · curated 25 Jul 2026
FlowGuard: From Signals to Evidence for MCP Security Detection
First reported arxiv.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
FlowGuard targets the fast-growing MCP attack surface where LLM agents interact with file systems, databases, and cloud services, offering defenders a way to distinguish real exploitable risks from misleading signals produced by existing scanners.
FlowGuard is an evidence-grounded MCP security detection system that verifies execution-related risks (like command injection and file system access) through runtime evidence rather than suspicious semantic signals alone, and detects semantic risks in tool metadata and returned content. Evaluated on a 1,880-case executable benchmark across five vulnerability categories, it achieves F1 scores of 0.879 and 0.942 on Command Injection and File System Access, reduces latency up to 2.23x versus existing dynamic scanners, and reported 523 findings across 326 real-world servers.