What it does
HarnessScope is an MCP resource that provides turn-level governance observability for Claude Code transcripts. The publisher describes it as local-first and as containing no LLM.
The publisher's description is the only information available for this entry, so no further details on setup, requirements or use cases are listed 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
HarnessScope
Turn-level governance observability for Claude Code transcripts. Local-first, no LLM inside.
v0.1.3As shown on registry.modelcontextprotocol.io when we last read it