evidence-report-mcp gives agents an evidence report before they act: what was checked, where it came from, and what was not checked.
Get startedFirst, add it to Claude Code.
claude mcp add evidence-report -- npx -y evidence-report-mcpThen let the agent hand over what it is about to use.
{ "kind": "package", "ecosystem": "npm",
"name": "lodash", "version": "4.17.20" }Read where the answer stops.
Known advisories from OSV.dev.Severity from each advisory's own rating or CVSS vector.
Records against their contract, units included.JSON Schema in strict mode, with x-unit: lbf*s is not N*s.
Content credentials, through c2patool.Only a trusted signer passes. No manifest proves nothing.
Two independent source domains, at least.Heuristic, so it can fail a claim but never pass one.
claude mcp add evidence-report -- npx -y evidence-report-mcpRead the guide