Agent Observability MCP
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
no price published
github.com/KryptosAI · 3 listed services · provider site
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
MCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF.
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
Provider identity is derived from the domain or repository in the source record. If two vendors share a host, they appear together here — that is a limitation of the data, not a statement about ownership.