{"id":"jeremydev87-codingbuddy","name":"codingbuddy","af_score":43.8,"security_score":27.0,"reliability_score":23.8,"what_it_does":"Codingbuddy is an MCP server (CLI distributed via npm) that orchestrates multi-agent review and implementation cycles (PLAN → ACT → EVAL, with AUTO mode) to enforce coding quality gates and produce session impact telemetry.","best_when":"You want repeatable quality checks across multiple AI coding tools via a single MCP server workflow and value audit-like session summaries.","avoid_when":"You need strict guarantees about security posture, uptime, or formal reliability guarantees without verifying the implementation/docs yourself.","last_evaluated":"2026-03-30T15:29:55.929981+00:00","has_mcp":true,"has_api":false,"auth_methods":["None specified (local CLI/MCP orchestration)"],"has_free_tier":false,"known_gotchas":["Workflow-oriented orchestration (PLAN/ACT/EVAL/AUTO) may cause multiple tool calls and increased costs; verify adapter behavior per supported AI tool.","Quality gates depend on agent/rule correctness; ensure your project context and configuration (codingbuddy.config.json) are appropriate.","MCP tool-calling coverage and error semantics are not evidenced in the provided documentation excerpt; integration may require trial and logging."],"error_quality":0.0}