{"id":"bbak-mcs-mcp","name":"mcs-mcp","af_score":60.0,"security_score":56.2,"reliability_score":30.0,"what_it_does":"An MCP server (Go binary) that ingests Atlassian Jira board issue transition history, reconstructs workflow semantics, and serves Monte-Carlo/flow diagnostics to AI agents (e.g., forecasting completion dates, capacity/bottleneck analysis, stability/predictability via control charts).","best_when":"You run an MCP-capable agent locally/privately and want offline-capable, board-scoped Jira flow analytics and forecasting based on event histories.","avoid_when":"You cannot guarantee consistent workflow status sets/order across analyzed issue types, or you require formal REST/GraphQL interfaces with standard cloud reliability guarantees.","last_evaluated":"2026-03-30T15:40:57.142730+00:00","has_mcp":true,"has_api":false,"auth_methods":["Jira API via Personal Access Token (PAT)","Jira API via Cloud API token + user email","Session cookies (fallback)"],"has_free_tier":false,"known_gotchas":["Workflow discovery assumption: all work item types on a board share the same workflow and status order; mixed workflows may yield unpredictable analytics.","Server currently works on Boards and does not accept passing JQL; recommended workaround is creating a board using query as board-JQL.","Cookie-based Jira auth may break due to expiry/anti-bot measures; prefer PAT/API token modes for stability.","Beta warning: forecasting/math is not thoroughly verified; agent should treat forecasts as provisional and not as a hard decision basis.","Experimental mode requires both env gate (MCS_ALLOW_EXPERIMENTAL) and per-session tool activation; forgetting one step changes behavior."],"error_quality":0.0}