Categories › AI & Agents › Multi-agent, orchestration & workflows
Task contract, evidence check and done gate for AI coding agents. Read-only, no sign-in.
Remote server: your requests and data go to mcp.nobrainer.tech. Claude Code: claude mcp add --transport http nobrainer-tech-flow https://mcp.nobrainer.tech/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
start_flow_task — Use at the start of a non-trivial task. Checks your proposed outcome and definition of done (DoD) against Flow's contract rules, chooses theget_flow_step — Use when you need guidance on a Flow stage, an event (e.g. blocked), a module (e.g. nobrainer-review), or a PR's Definition of Done or readicheck_flow_evidence — Use after running a check. Validates one to four evidence records against DoD items in the contract token: exit codes, test counts in the oucheck_flow_done — Use before saying a task is done. Returns DONE only when every DoD item has accepted, current evidence, DONE_WITH_GAPS when the rest are lisdraft_flow_handoff — Use after check_flow_done. Returns a short final-report skeleton from the done receipt: delivered outcome, proof per DoD item, what was not recommend_flow_model — Use when picking a model for a Flow task: top-3 from a pinned NoBrainer benchmark snapshot, no invented scores.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.