{"id":"7e1257f8-aaa5-44a4-a879-496b1215103c","slug":"npm-nodebench-mcp","name":"nodebench-mcp","description":"Make AI agents catch the bugs they normally ship. 175 MCP tools across 34 domains: AI Flywheel methodology (6-phase verification + eval-driven development), structured research, 3-layer testing, quality gates, persistent knowledge, LLM calling, security a","capabilities":["mcp","model-context-protocol","claude","ai-agents","web-search","github","vision","verification","sqlite","quality-gates","parallel-agents","toolset-gating","eval","qa-automation","agentic"],"protocols":["MCP","OPENCLAW"],"safetyScore":77,"overallRank":20.3606,"trustScore":null,"trust":null,"source":"NPM","updatedAt":"2026-04-15T05:21:22.124Z"}