NoBrainer Tech Flow
Server Details
Task contract, evidence check and done gate for AI coding agents. Read-only, no sign-in.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- nobrainer-tech/nobrainer-tech-flow
- GitHub Stars
- 7
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool has a distinct role in the Flow lifecycle (start, guidance, evidence validation, done gate, handoff, model pick). The only real overlap is between check_flow_done and check_flow_evidence, both 'check' verbs operating on DoD items, but their descriptions clarify the ordering (evidence after a check, done before declaring completion).
Every name follows the same verb_flow_noun pattern: check_flow_done, check_flow_evidence, draft_flow_handoff, get_flow_step, recommend_flow_model, start_flow_task. All snake_case with a consistent domain infix, making the pattern predictable.
Six tools is well within the ideal range and each maps to a clear stage of the Flow workflow. No tool feels redundant or bolted on; the model-recommendation tool is the only auxiliary one and it supports a distinct need.
The surface covers the full lifecycle: start_flow_task (contract), get_flow_step (guidance/resume), check_flow_evidence (validation), check_flow_done (gate), and draft_flow_handoff (reporting). Minor gaps exist — there is no explicit tool to amend or re-list contract DoD items, and state persistence is left to the caller's goal file.
Available Tools
6 toolscheck_flow_doneCheck whether the task is doneARead-onlyIdempotentInspect
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 listed in unchecked with a reason, otherwise NOT_DONE with the exact missing items.
Inputs: token (required), unchecked.
check_flow_evidenceCheck evidence for DoD itemsARead-onlyIdempotentInspect
Use after running a check. Validates one to four evidence records against DoD items in the contract token: exit codes, test counts in the output, hashes, URL status and evidence level. It cannot see your machine; it checks structure and consistency only. Returns verdicts and an updated token.
Inputs: token (required), evidence (required).
draft_flow_handoffDraft the final handoffARead-onlyIdempotentInspect
Use after check_flow_done. Returns a short final-report skeleton from the done receipt: delivered outcome, proof per DoD item, what was not checked, decisions left to the user and the next action.
Inputs: receipt (required).
get_flow_stepGet the next Flow stepARead-onlyIdempotentInspect
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 readiness (topic pr_dod). Returns up to six rules quoted from the pinned release, with their source. With a token, event resume also returns a goal block.
Inputs: event, stage, token, topic, +1 more.
recommend_flow_modelRecommend Flow modelARead-onlyIdempotentInspect
Use when picking a model for a Flow task: top-3 from a pinned NoBrainer benchmark snapshot, no invented scores.
Inputs: task (required), have, role, priority.
start_flow_taskStart a Flow taskARead-onlyIdempotentInspect
Use at the start of a non-trivial task. Checks your proposed outcome and definition of done (DoD) against Flow's contract rules, chooses the quick or full path, and returns DoD item IDs, a signed contract token and the first step. Computes only; stores nothing. Save the token in your goal file.
Inputs: dod (required), outcome (required), risks, non_goals, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
6 tool updates
- First observed
check_flow_done - First observed
check_flow_evidence - First observed
draft_flow_handoff - First observed
get_flow_step - First observed
recommend_flow_model - First observed
start_flow_task
Related MCP Connectors
Hand tasks, bugs and finished work to AI coding agents, and get back a write-up with evidence.
Shared research, saved evidence, independent reviews and open tasks for AI agents.
Task tracking built for coding agents. Work is leased, so two agents never take the same SubTask.
Search, reuse, verify AI reasoning. Task marketplace with leaderboard. Zero-barrier, no auth.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables coding agents and humans to share a gated task registry where tasks move through a strict status flow and transitions require verification and review evidence from distinct identities.1731 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceEnables a requester's AI delegate and an assignee's coding agent to settle whether a task is done on a shared board, exchanging only typed messages (contract, question, answer, evidence, verdict) instead of ticket comments. It enforces a verifiable done contract with required evidence, re-runs checks to verify that evidence, bounds negotiation to three rounds, and escalates to the humans in a single batched notification when the mandate runs out.1Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables AI coding providers to run structured multi-agent workflows by claiming tasks, logging actions, managing handoffs, and enforcing server-side health gates across explorer, consultant, builder, and reviewer roles. Specifications stay as Markdown on disk while tracked task state, acceptance evidence, and completion checks are owned by the server.29 npmMIT
- AlicenseAqualityBmaintenanceShared task ledger for AI agents and humans: atomic claims, state machine, GitHub and Slack sync.6363MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.