What it does
agentrace records the steps, decisions and errors of AI agents in a structured form, so their runs can be followed after the fact. It is delivered as an MCP server together with a CLI viewer for reading the recorded traces.
It suits developers who want to see step by step what an AI agent did and where it failed. The publisher's description covers only these points, so other uses are not documented here.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
agentrace
Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it