_ registry / mcp + a2a streamable-http · checked 1h ago

com.monopoly-gold.planner/mcp

https://planner.monopoly-gold.com

Registry code: 8462d9715f9e0fb6

api record

Planner MCP by Monopoly Gold is the official com.monopoly-gold.planner/mcp server at https://planner.monopoly-gold.com/_mcp. For a Planner goal URL, do not browse the UI: extract the UUID after /goal/ and call goal-get with it as required goalId. In Codex run codex mcp add planner --url https://planner.monopoly-gold.com/_mcp, then codex mcp login planner for browser OAuth; never request or paste a Planner API token. Verify with codex mcp list and project-list.

endpoint
https://planner.monopoly-gold.com/_mcp
door code
a615442307146482
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing
karma
0 · newcomer
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
491ms

last good check

priced tools
0

of 43 tools

_ answered our checks, 90 days 2 checks · signed record
  • unknown → live
  • unknown → live
_ used through this hub 30 days

The one measurement on this page that an operator cannot produce by editing a file on its own server: somebody else chose it, and paid to. Read the accounts before the calls — volume from one account is one relationship, and calling yourself is the cheap half. Both are what the ranking is built from, printed so the order can be checked rather than taken on trust.

accounts
0

distinct, expensive to fake

calls served
0

successful, last 30 days

_ what it can do 43 tools
1 auth-required 42 never probed 1 of 43 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • goal-list auth-required 1h ago

    List goals with optional filters: projectId (UUID), status (backlog/checking_ac/checking_ac_failed/checking_ac_errored/ready_for_work/in_progress/blocked/done/cancelled), type (goal/milestone/task/habit), parentId (UUID — direct children only). Returns up to limit results (default 50, no offset pagination). Sorted by priority ASC then createdAt DESC. Each entry has id, title, webUrl, status, priority, type, progress, parent_id, project_id.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "default": null,
      "description": "Тип: goal, milestone, task, habit"
    },
    "limit": {
      "type": "integer",
      "default": null,
      "description": "Макс. кол-во результатов (default: 50)"
    },
    "status": {
      "type": "string",
      "default": null,
      "description": "Статус: backlog, checking_ac, checking_ac_failed, checking_ac_errored, ready_for_work, in_progress, blocked, done, cancelled"
    },
    "parentId": {
      "type": "string",
      "default": null,
      "description": "UUID родителя (только прямые дети)"
    },
    "projectId": {
      "type": "string",
      "default": null,
      "description": "UUID проекта (фильтр)"
    }
  }
}
    arguments 30 lines
  • goal-summary unknown never probed

    Aggregate statistics across all goals (or scoped to a projectId): total count, breakdown by status, root count, blocked count, and overdue count. Useful for daily standups and dashboard views.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "default": null,
      "description": "UUID проекта"
    }
  }
}
    arguments 10 lines
  • goal-remove-assumption unknown never probed

    Remove an assumption from a goal edge.

    mcp-tool

    {
  "type": "object",
  "required": [
    "assumptionId"
  ],
  "properties": {
    "assumptionId": {
      "type": "string",
      "description": "UUID допущения"
    }
  }
}
    arguments 12 lines
  • goal-request-ac-change unknown never probed

    Request a change to an acceptance criterion. grounds=unreachable (default): the AC cannot be proven — requires ≥3 failed evidence attempts (weak/mismatch) with 0 matches. grounds=wrong_criterion: the AC measures the wrong thing (owner never approved this wording, or a revealed fact shows it tracks something else) — no failed attempts required, but you MUST pass quotedFragment: a verbatim slice of the criterion text you claim is wrong (checked against the stored text), and the reason must name the unapproved wording or the finding; difficulty alone is rejected. An LLM judge screens the reason either way. On pass, creates an escalation for the goal owner to resolve (edit AC text, split to sub-goal, drop AC without creating a child, or reject). Grove mode only, goal must be in_progress.

    mcp-tool

    {
  "type": "object",
  "required": [
    "criterionId",
    "reason"
  ],
  "properties": {
    "reason": {
      "type": "string",
      "description": "Structured justification. For unreachable: what is\nunreachable and what was attempted. For wrong_criterion:\nwhich wording/threshold the owner never approved, or what\nfinding showed the criterion measures something else"
    },
    "grounds": {
      "type": "string",
      "default": "unreachable",
      "description": "Subject of the request: 'unreachable' (default) or 'wrong_criterion'"
    },
    "criterionId": {
      "type": "string",
      "description": "UUID of the acceptance criterion to escalate"
    },
    "quotedFragment": {
      "type": "string",
      "default": null,
      "description": "Verbatim slice of the criterion text claimed to be\nwrong — required when grounds=wrong_criterion,\nignored otherwise"
    }
  }
}
    arguments 27 lines
  • goal-add-note unknown never probed

    Add a free-form note (markdown supported) to a goal — decisions taken, dead ends hit, context worth carrying into the next session. Notes are NOT evidence: they hang off the goal rather than an acceptance criterion and never count toward AC coverage or closing a Grove goal — use goal-attach-evidence for proof. Notes are visible in the goal detail panel and returned by goal-get under notes[].

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId",
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Текст заметки (markdown)"
    },
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    }
  }
}
    arguments 17 lines
  • goal-remove-note unknown never probed

    Remove a note from a goal by note UUID. Note ids come from goal-get (notes[].id). Deletes only the note — never touches acceptance criteria, evidence or blockers.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId",
    "noteId"
  ],
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "noteId": {
      "type": "string",
      "description": "UUID заметки"
    }
  }
}
    arguments 17 lines
  • goal-tree unknown never probed

    Fetch the full goal hierarchy as a nested tree. Optional filters: projectId (UUID) to scope to one project, rootId (UUID) to get a subtree. Each node includes id, title, status, priority, type, progress, and nested children array.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "rootId": {
      "type": "string",
      "default": null,
      "description": "UUID корня поддерева"
    },
    "projectId": {
      "type": "string",
      "default": null,
      "description": "UUID проекта (по умолчанию: все проекты)"
    }
  }
}
    arguments 15 lines
  • goal-add-criterion unknown never probed

    Append an acceptance criterion to a goal. The text must describe an observable check over an artifact (e.g. "GET /api/health returns 200 with {status:ok}"), not a subjective approval. Each criterion has a class: pre-merge (default — proved in CI / by attached evidence) or post-deploy (proved by an executable probe against the deployed prod instance). A post-deploy criterion MUST carry probeSpec {method, url, expect:{http_code, body:{field: expectedValue}}} — the request the runner sends and the answer it must get; without it the call is rejected with error=probe_required. Passing probeSpec alone implies probeClass=post-deploy. Set visualEvidenceSuggested=true only when adopting visualAcSuggestion from goal-create, goal-get, or the ready_for_work advisory returned by goal-update; it remains an ordinary AC. Grove mode: AC (class and probe included) can only be added while goal is in backlog, except accepting a visual advisory in ready_for_work: that starts a direct checking_ac recheck, without intermediate backlog. Other edits are frozen once started; quality linter blocks high-severity issues. Standard mode: AC editable until goal is closed, linter is advisory. Returns criterion id, position, text, probeClass, probeSpec and any quality findings.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId",
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Формулировка критерия"
    },
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "position": {
      "type": "integer",
      "default": null,
      "description": "Позиция (default = append в конец)"
    },
    "probeSpec": {
      "default": null,
      "properties": {
        "url": {
          "type": "string",
          "description": "Absolute http(s) URL the runner requests on the deployed instance"
        },
        "expect": {
          "type": "object",
          "properties": {
            "body": {
              "type": "object",
              "additionalProperties": true
            },
            "http_code": {
              "type": "integer",
              "maximum": 599,
              "minimum": 100
            }
          },
          "description": "What the response must contain: http_code (exact) and/or body (subset of fields with expected scalar values; nested objects = nested fields; \"{{deployed_revision}}\" = SHA of the revision that triggered the probe)"
        },
        "method": {
          "enum": [
            "GET",
            "HEAD"
          ],
          "type": "string",
          "description": "HTTP method of the probe request"
        }
      },
      "description": "Исполнимая проба post-deploy критерия: {method: GET|HEAD|POST|PUT|PATCH|DELETE, url: абсолютный http(s), expect: {http_code: 200, body: {field: expectedValue, nested: {field: value}}}}. Ожидаемые значения фиксируются сейчас; единственная подстановка времени прогона — \"{{deployed_revision}}\" (SHA развёрнутой ревизии). Пример: {\"method\":\"GET\",\"url\":\"https://planner.monopoly-gold.com/api/healthz\",\"expect\":{\"http_code\":200,\"body\":{\"status\":\"ok\",\"revision\":\"{{deployed_revision}}\"}}}"
    },
    "probeClass": {
      "enum": [
        "pre-merge",
        "post-deploy",
        null
      ],
      "type": "string",
      "default": null,
      "description": "Класс критерия: pre-merge (default; доказывается в CI / приложенным evidence) или post-deploy (доказывается исполнимой пробой против прода; требует probeSpec)"
    },
    "visualEvidenceSuggested": {
      "type": "boolean",
      "default": false,
      "description": "True only when this AC accepts Planner's visual-AC advisory"
    }
  }
}
    arguments 70 lines
  • goal-add-assumption unknown never probed

    Add an assumption to a goal edge (parent→this goal). An assumption is an explicit premise: "why does completing this goal contribute to the parent?" Requires the goal to have a parent (root goals have no edge). Text must pass quality linter (testable, precise, discrete, signposted). Type (cause_effect/causal_link) is auto-classified by LLM.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId",
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Формулировка допущения"
    },
    "goalId": {
      "type": "string",
      "description": "UUID цели (ребёнка — assumption живёт на ребре parent→child)"
    },
    "signpost": {
      "type": "string",
      "default": null,
      "description": "Наблюдаемый индикатор провала (опционально)"
    }
  }
}
    arguments 22 lines
  • goal-update-assumption unknown never probed

    Update text or signpost of an assumption. Status cannot be changed manually — transitions happen only via evidence judge verdicts.

    mcp-tool

    {
  "type": "object",
  "required": [
    "assumptionId"
  ],
  "properties": {
    "text": {
      "type": "string",
      "default": null,
      "description": "Новый текст допущения"
    },
    "signpost": {
      "type": "string",
      "default": null,
      "description": "Новый индикатор провала"
    },
    "assumptionId": {
      "type": "string",
      "description": "UUID допущения"
    }
  }
}
    arguments 22 lines
  • goal-suggest-assumptions unknown never probed

    LLM generates suggested assumptions for a goal edge (parent→child). Returns 2-4 assumptions with signposts and type classification. Author should review, edit, and accept relevant ones via goal-add-assumption.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId"
  ],
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели (ребёнка)"
    }
  }
}
    arguments 12 lines
  • goal-attach-assumption-evidence unknown never probed

    Attach text evidence to an assumption and judge it. The judge evaluates whether the evidence supports or challenges the assumption and automatically transitions its status: supports → supported, first challenges → challenged, second (repeat) challenges → invalidated. Invalidated is terminal — further evidence no longer moves the status. Judge infra failures fail open (errored verdict, no status change).

    mcp-tool

    {
  "type": "object",
  "required": [
    "assumptionId",
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Текст evidence — наблюдение/данные, подтверждающие или опровергающие допущение"
    },
    "assumptionId": {
      "type": "string",
      "description": "UUID допущения"
    }
  }
}
    arguments 17 lines
  • goal-recent-unresolved unknown never probed

    Pull-инбокс для «подхватить и довести» в неосновное окно. По одному проекту, за окно N дней, статусы для подхвата (очередь исполнителя — ready_for_work и checking_ac_errored: backlog-цели брать нельзя). Возвращает обогащённые записи (title/description-preview/parent/counts), чтобы выбрать без goal-get. Параметры: project (slug, required), withinDays (int, default 14), statuses (list, default ["backlog"]; допустимо {backlog,checking_ac,checking_ac_failed,checking_ac_errored,ready_for_work,in_progress,blocked}), limit (int, default 10).

    mcp-tool

    {
  "type": "object",
  "required": [
    "project"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": null,
      "description": "Сколько записей вернуть, default 10"
    },
    "project": {
      "type": "string",
      "description": "Slug проекта"
    },
    "statuses": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "default": null,
      "description": "Подмножество {backlog,checking_ac,checking_ac_failed,checking_ac_errored,ready_for_work,in_progress,blocked}, default [\"backlog\"]"
    },
    "withinDays": {
      "type": "integer",
      "default": null,
      "description": "Окно свежести (createdAt), default 14"
    }
  }
}
    arguments 30 lines
  • goal-record-iteration-certificate unknown never probed

    Record one completed LeanSolver iteration against the current tracked contract. Result artifact refs must resolve to existing evidence or goal_attachment rows owned by this goal. Rework iterations accept only registered finding IDs and require a separate judged evidence row as repeatCheckEvidenceId; Planner derives the repeat verdict server-side. Only certificates admitted here may affect the numeric implementation rework rate.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId",
    "reworkClass",
    "afterFingerprint",
    "precondition",
    "action",
    "outcome",
    "acVerdict",
    "artifactRefs"
  ],
  "properties": {
    "action": {
      "type": "string",
      "description": "Action that changed the result"
    },
    "goalId": {
      "type": "string",
      "description": "Goal UUID"
    },
    "outcome": {
      "type": "string",
      "description": "Observable completed result"
    },
    "acVerdict": {
      "type": "string",
      "description": "matches, weak, mismatch, or errored"
    },
    "reworkClass": {
      "type": "string",
      "description": "implementation, contract, proof_only, or unknown"
    },
    "artifactRefs": {
      "type": "array",
      "items": {},
      "description": "Existing goal-owned evidence/goal_attachment refs"
    },
    "precondition": {
      "type": "string",
      "description": "Observable state before the iteration"
    },
    "coverageDelta": {
      "type": "array",
      "items": {},
      "default": [],
      "description": "Structured coverage change"
    },
    "afterFingerprint": {
      "type": "string",
      "description": "Lowercase SHA-256 of the completed result"
    },
    "beforeFingerprint": {
      "type": "string",
      "default": null,
      "description": "Optional lowercase SHA-256 of the prior result"
    },
    "addressesFindingIds": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "default": [],
      "description": "Registered finding UUIDs addressed by this iteration"
    },
    "repeatCheckEvidenceId": {
      "type": "string",
      "default": null,
      "description": "Separate judged evidence UUID; mandatory when findings are addressed"
    }
  }
}
    arguments 72 lines
  • project-add-dependency unknown never probed

    Declare that one project depends on another (depends-on relationship). Accepts UUID or slug for both sides. Idempotent: if the dependency already exists, returns it with already_existed=true. Self-references are rejected. No cycle detection — the caller is responsible for avoiding circular chains.

    mcp-tool

    {
  "type": "object",
  "required": [
    "projectId",
    "dependsOnProjectId"
  ],
  "properties": {
    "projectId": {
      "type": "string",
      "description": "UUID или slug проекта-зависимого"
    },
    "dependsOnProjectId": {
      "type": "string",
      "description": "UUID или slug проекта, от которого зависит"
    }
  }
}
    arguments 17 lines
  • project-remove-dependency unknown never probed

    Remove a project dependency. Two lookup modes: pass dependency_id (UUID of the link itself), or pass both projectId and dependsOnProjectId (UUID or slug). Returns removed=true on success, removed=false if the dependency was not found.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "default": null,
      "description": "UUID или slug проекта-зависимого (если dependencyId не задан)"
    },
    "dependencyId": {
      "type": "string",
      "default": null,
      "description": "UUID самой связи"
    },
    "dependsOnProjectId": {
      "type": "string",
      "default": null,
      "description": "UUID или slug целевого проекта (если dependencyId не задан)"
    }
  }
}
    arguments 20 lines
  • goal-move unknown never probed

    Move a goal to a different parent or project. Pass newParentId=UUID to reparent (inherits project from new parent), newParentId=null to make root. Optional projectId=UUID overrides the target project when making root (cross-project move to root). Cascades project change to all descendants. Prevents cycles.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId"
  ],
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID перемещаемой цели"
    },
    "projectId": {
      "type": "string",
      "default": null,
      "description": "UUID целевого проекта (используется при newParentId=null для cross-project move в корень)"
    },
    "newParentId": {
      "type": "string",
      "default": null,
      "description": "UUID нового родителя (null = сделать root)"
    }
  }
}
    arguments 22 lines
  • goal-reorder unknown never probed

    Set display order of sibling goals within the same parent and priority band. Pass an array of goal UUIDs in the desired order — each is assigned position = its array index. All goals must share the same parent and priority.

    mcp-tool

    {
  "type": "object",
  "required": [
    "ids"
  ],
  "properties": {
    "ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "UUID целей в новом порядке (все должны иметь одного родителя и одинаковый priority)"
    }
  }
}
    arguments 15 lines
  • goal-get unknown never probed

    Fetch full details of a single goal: title, description, status, priority, type, mode, children, acceptance criteria (with evidence coverage), blockers, tags, deadline, estimate, history log, and project. The primary drill-down tool after goal-list or goal-tree. For a Planner goal URL, do not browse the UI: extract the UUID after /goal/ and pass it as required goalId.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId"
  ],
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    }
  }
}
    arguments 12 lines
  • goal-update unknown never probed

    Partial update of a goal — only the fields you pass are changed; omitted fields are untouched. Updatable: title, status, priority (1-5), description, type, tags, deadline, estimate, mode, attemptCommit (git SHA of the attempt commit; once a deployed revision contains it, post-deploy probes of this goal run automatically and record machine verdicts — pass "" to clear), dismissVisualAcSuggestion. Status transitions follow a matrix: backlog→ready_for_work (author; grove: requires ≥1 AC, red-team check when the project requires it — the goal parks in checking_ac and becomes ready_for_work, checking_ac_failed (hole in AC set) or checking_ac_errored (check did not run)); ready_for_work|checking_ac_errored→in_progress (executor, no checks); in_progress→done (file-evidence on every AC + session_history) | blocked | cancelled. A visible-UI goal with an outstanding visualAcSuggestion returns an advisory before ready_for_work freezes the AC contract: accept it through goal-add-criterion(visualEvidenceSuggested=true), or retry this same update with dismissVisualAcSuggestion=true. The first MCP dismissal persists the choice and notifies Product Events with the goal title and link, full proposed AC, and why screenshot proof was useful; UI, repeat, and no-active dismissals are silent, and notification failures do not undo the dismissal. backlog→in_progress and backlog→done are rejected. Returns the updated goal with all fields.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId"
  ],
  "properties": {
    "mode": {
      "type": "string",
      "default": null,
      "description": "Режим цели: standard или grove. Иммутабелен после mode_locked_at"
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "default": null,
      "description": "Новые теги"
    },
    "type": {
      "type": "string",
      "default": null,
      "description": "Новый тип: goal, milestone, task, habit"
    },
    "title": {
      "type": "string",
      "default": null,
      "description": "Новое название (макс. 500)"
    },
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "status": {
      "type": "string",
      "default": null,
      "description": "Новый статус: backlog, ready_for_work, in_progress, blocked, done, cancelled (checking_ac* выставляет система)"
    },
    "deadline": {
      "type": "string",
      "default": null,
      "description": "Новый дедлайн (ISO 8601)"
    },
    "estimate": {
      "type": "string",
      "default": null,
      "description": "Новая оценка"
    },
    "priority": {
      "type": "integer",
      "default": null,
      "description": "Новый приоритет (1–5)"
    },
    "description": {
      "type": "string",
      "default": null,
      "description": "Новое описание"
    },
    "attemptCommit": {
      "type": "string",
      "default": null,
      "description": "git SHA коммита попытки (7–64 hex). Когда развёрнутая ревизия содержит его (предок, не равенство), post-deploy пробы цели стартуют сами по событию деплоя; повторная установка = новая попытка (отметки доставки и пробы сбрасываются); \"\" снимает"
    },
    "dismissVisualAcSuggestion": {
      "type": "boolean",
      "default": null,
      "description": "Отклонить advisory visual-AC; для ready_for_work это явный выбор «продолжить без предложения»"
    }
  }
}
    arguments 70 lines
  • goal-delete unknown never probed

    IRREVERSIBLY delete a goal and all its descendants (children, evidence, blockers). Prefer goal-update status=cancelled to preserve history, or goal-block to mark an obstacle. Use delete only for erroneous/duplicate entries. Returns the deleted title and children_deleted count.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId"
  ],
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    }
  }
}
    arguments 12 lines
  • goal-register-iteration-finding unknown never probed

    Register an immutable LeanSolver finding against the currently tracked goal contract. subjectRefs must be goal-scoped refs of kind goal, criterion, or assumption. Returns the server-generated finding id to pass later as addressesFindingId; rejects stale contract tracking.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId",
    "kind",
    "summary",
    "subjectRefs"
  ],
  "properties": {
    "kind": {
      "type": "string",
      "description": "evidence_mismatch, red_team_hole, assumption_invalidated, acceptance_gap, or manual_checkpoint"
    },
    "goalId": {
      "type": "string",
      "description": "Goal UUID"
    },
    "summary": {
      "type": "string",
      "description": "Concise observable weakness or gap"
    },
    "sourceRefs": {
      "type": "array",
      "items": {},
      "default": [],
      "description": "Optional immutable source refs (validated structurally; resolved by the certificate recorder)"
    },
    "subjectRefs": {
      "type": "array",
      "items": {},
      "description": "Goal-scoped subject refs"
    }
  }
}
    arguments 34 lines
  • goal-start-iteration-tracking unknown never probed

    Explicitly start LeanSolver iteration tracking for the goal contract currently stored by Planner. Planner computes the contract fingerprint server-side from title, description, acceptance criteria, and assumptions. Calling again without a contract change is idempotent; after a contract change it starts a new version while retaining old certificates as superseded history.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId"
  ],
  "properties": {
    "goalId": {
      "type": "string"
    }
  }
}
    arguments 11 lines
  • goal-resolve-escalation unknown never probed

    Resolve a pending AC escalation. Owner decides: edit (provide new AC text), split (move AC to a child goal), drop (remove the AC outright, optionally with a linkedGoalId audit reference), or reject (agent must find another way). All prior evidence on the AC is deleted for edit/split/drop so the agent must submit fresh proof.

    mcp-tool

    {
  "type": "object",
  "required": [
    "escalationId",
    "resolution"
  ],
  "properties": {
    "note": {
      "type": "string",
      "default": null,
      "description": "Optional comment explaining the decision"
    },
    "newText": {
      "type": "string",
      "default": null,
      "description": "New AC text (required when resolution=edit)"
    },
    "resolution": {
      "type": "string",
      "description": "One of: edit, split, drop, reject"
    },
    "escalationId": {
      "type": "string",
      "description": "UUID of the escalation to resolve"
    },
    "linkedGoalId": {
      "type": "string",
      "default": null,
      "description": "Optional UUID of an existing goal to record as an\naudit reference (only meaningful when resolution=drop)"
    },
    "overrideResolvedBy": {
      "type": "string",
      "default": null
    }
  }
}
    arguments 36 lines
  • goal-attach-file unknown never probed

    Attach a small file (mockup, diagram, screenshot, PDF) to a GOAL as a description attachment — NOT evidence: it is not bound to any acceptance criterion, is never judged and never counts toward closing the goal. Returns {attachment.url, attachment.markdown}; paste `markdown` into the goal description (goal-update description) and the web UI renders images inline. contentBase64 is reliable only for payloads ≤ ~1 KB (long string arguments get truncated on the agent side before the request is sent). For anything bigger call goal-request-upload with goalId and stream the file with a single PUT — same result shape, no base64.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId",
    "filename",
    "contentBase64"
  ],
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID of the goal the file illustrates"
    },
    "caption": {
      "type": "string",
      "default": null,
      "description": "Optional alt-text / caption used in the markdown fragment"
    },
    "filename": {
      "type": "string",
      "description": "Original file name (basename only; used for download + markdown alt)"
    },
    "mimeType": {
      "type": "string",
      "default": null,
      "description": "Optional MIME hint; server sniffs bytes when omitted or not whitelisted"
    },
    "createdBy": {
      "type": "string",
      "default": null,
      "description": "Identifier of the uploading agent"
    },
    "contentBase64": {
      "type": "string",
      "description": "File bytes, standard base64 (RFC 4648). Tiny files only — see description."
    },
    "contentSha256": {
      "type": "string",
      "default": null,
      "description": "Optional hex sha256 of the raw bytes — server fails fast on transport corruption"
    }
  }
}
    arguments 42 lines
  • goal-dismiss-red-team unknown never probed

    Dismiss the red-team finding that blocks a goal from starting, when you disagree with the verdict. Requires a reason of at least 80 characters explaining why the counterexample does not apply. The dismissal is recorded in goal history and surfaced in goal-get, so "agent overrode the gate" stays distinguishable from "no hole was found". Prefer fixing the acceptance criteria via goal-add-criterion — dismissing leaves the hole open.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId",
    "reason"
  ],
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "reason": {
      "type": "string",
      "description": "Почему контрпример неприменим — от 80 символов, попадёт в историю цели"
    }
  }
}
    arguments 17 lines
  • goal-read-evidence-content unknown never probed

    Read attached evidence through MCP without changing its format. Pass evidenceId from goal-get. Text (text/plain, JSON, NDJSON) returns newline-preserving redacted lines; offset/limit are zero-based line pagination. Images return a native MCP image with original MIME and bytes. For a complete video, PDF, ZIP or other binary, binaryDelivery=link (default) returns a resource_link to the authenticated original download — no base64 and no conversion. If the client cannot open external links, binaryDelivery=base64 embeds the exact original bytes in a resource blob; this expands data by about 33% plus JSON overhead and can consume the client context window, so use it only when needed. byteOffset/byteLimit require binaryDelivery=base64. Text secrets are redacted; binary evidence is unmodified.

    mcp-tool

    {
  "type": "object",
  "required": [
    "evidenceId"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 100,
      "description": "Number of whole lines to return (1–500)"
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "description": "Zero-based line offset"
    },
    "byteLimit": {
      "type": "integer",
      "default": null,
      "description": "Number of bytes to return for binary evidence; omit with byteOffset for the complete original"
    },
    "byteOffset": {
      "type": "integer",
      "default": null,
      "description": "Zero-based byte offset for binary evidence"
    },
    "evidenceId": {
      "type": "string",
      "description": "UUID of file-backed evidence from goal-get"
    },
    "binaryDelivery": {
      "enum": [
        "link",
        "base64"
      ],
      "type": "string",
      "default": "link",
      "description": "Complete binary: link to the original (default), or base64 fallback for clients without external links"
    }
  }
}
    arguments 41 lines
  • goal-todo unknown never probed

    Quick-capture a task or improvement idea into a project. Creates a backlog task with priority 4 (low) and auto-adds the "suggestion" tag. Resolves project by slug (falls back to the default project). Lightweight alternative to goal-create when you need minimal ceremony.

    mcp-tool

    {
  "type": "object",
  "required": [
    "title"
  ],
  "properties": {
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "default": null,
      "description": "Теги (автоматически добавляется \"suggestion\")"
    },
    "title": {
      "type": "string",
      "description": "Название задачи"
    },
    "project": {
      "type": "string",
      "default": null,
      "description": "Slug проекта (если не указан — используется дефолтный)"
    },
    "priority": {
      "type": "integer",
      "default": null,
      "description": "Приоритет 1–5 (default: 4)"
    },
    "description": {
      "type": "string",
      "default": null,
      "description": "Описание"
    }
  }
}
    arguments 35 lines
  • project-create unknown never probed

    Create a new project container for goals. Requires title and a unique slug (lowercase a-z, 0-9, hyphens). Optional: description, status (active/archived/paused, default active), tags, icon (emoji), repositoryPath, repositoryUrl, sourceRef ({type:"git",url,ref} — remote-research source), isDefault. Returns the created project with id, slug, and webUrl. Slug must be unique — duplicates are rejected with existing slugs list.

    mcp-tool

    {
  "type": "object",
  "required": [
    "title",
    "slug"
  ],
  "properties": {
    "icon": {
      "type": "string",
      "default": null,
      "description": "Иконка (эмодзи, макс. 10 символов)"
    },
    "slug": {
      "type": "string",
      "description": "Уникальный slug (только a-z, 0-9, дефис)"
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "default": null,
      "description": "Теги"
    },
    "title": {
      "type": "string",
      "description": "Название проекта"
    },
    "status": {
      "type": "string",
      "default": null,
      "description": "Статус: active / archived / paused (default: active)"
    },
    "isDefault": {
      "type": "boolean",
      "default": null,
      "description": "Сделать проектом по умолчанию"
    },
    "sourceRef": {
      "type": "object",
      "default": null,
      "description": "Источник кода для remote-research: {type:\"git\",url,ref}"
    },
    "description": {
      "type": "string",
      "default": null,
      "description": "Описание проекта"
    },
    "repositoryUrl": {
      "type": "string",
      "default": null,
      "description": "URL репозитория"
    },
    "repositoryPath": {
      "type": "string",
      "default": null,
      "description": "Путь к репозиторию на сервере"
    }
  }
}
    arguments 60 lines
  • project-get unknown never probed

    Fetch full project details: title, slug, status, description, icon, tags, repository info, sourceRef ({type,url,ref} for remote-research or null), goals breakdown by status (backlog/in_progress/blocked/done/cancelled counts), and depends_on list of project dependencies.

    mcp-tool

    {
  "type": "object",
  "required": [
    "projectId"
  ],
  "properties": {
    "projectId": {
      "type": "string",
      "description": "UUID проекта"
    }
  }
}
    arguments 12 lines
  • project-update unknown never probed

    Partial update of a project — only the fields you pass are changed; omitted fields are untouched. Updatable: title, slug, description, status (active/archived/paused), tags, icon (emoji), repositoryPath, repositoryUrl, sourceRef ({type:"git",url,ref} — remote-research source), clearSourceRef (true → сбрасывает Project.sourceRef в null; несовместим с sourceRef), isDefault, redTeamMode (optional/advisory/required), evidenceJudgeMode (off/optional/required), allowedGoalMode (any/grove_only), fmeaGenerationMode (off/on), escalationResolveTimeout (off/1h/4h/24h), escalationAutoResolveBy (none/planner-agent), escalationAutoResolveStrategy (suggest-edit/reject-default). Returns the updated project with all fields.

    mcp-tool

    {
  "type": "object",
  "required": [
    "projectId"
  ],
  "properties": {
    "icon": {
      "type": "string",
      "default": null,
      "description": "Иконка (эмодзи, макс. 10 символов)"
    },
    "slug": {
      "type": "string",
      "default": null,
      "description": "Новый slug (только a-z, 0-9, дефис; должен быть уникальным)"
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "default": null,
      "description": "Новые теги"
    },
    "title": {
      "type": "string",
      "default": null,
      "description": "Новое название"
    },
    "status": {
      "type": "string",
      "default": null,
      "description": "Новый статус: active, archived, paused"
    },
    "isDefault": {
      "type": "boolean",
      "default": null,
      "description": "Сделать проектом по умолчанию"
    },
    "projectId": {
      "type": "string",
      "description": "UUID проекта"
    },
    "sourceRef": {
      "type": "object",
      "default": null,
      "description": "Источник кода для remote-research: {type:\"git\",url,ref}"
    },
    "description": {
      "type": "string",
      "default": null,
      "description": "Новое описание"
    },
    "redTeamMode": {
      "type": "string",
      "default": null,
      "description": "Режим red-team: optional, advisory, required"
    },
    "repositoryUrl": {
      "type": "string",
      "default": null,
      "description": "URL репозитория"
    },
    "clearSourceRef": {
      "type": "boolean",
      "default": null,
      "description": "Установить sourceRef в null (отвязать репозиторий); несовместим с sourceRef"
    },
    "repositoryPath": {
      "type": "string",
      "default": null,
      "description": "Путь к репозиторию на сервере"
    },
    "allowedGoalMode": {
      "type": "string",
      "default": null,
      "description": "Разрешённые режимы целей: any, grove_only"
    },
    "evidenceJudgeMode": {
      "type": "string",
      "default": null,
      "description": "Режим судьи доказательств: off, optional, required"
    },
    "fmeaGenerationMode": {
      "type": "string",
      "default": null,
      "description": "FMEA-генерация: off, on"
    },
    "escalationAutoResolveBy": {
      "type": "string",
      "default": null,
      "description": "Авто-резолвер эскалации: none, planner-agent"
    },
    "escalationResolveTimeout": {
      "type": "string",
      "default": null,
      "description": "Таймаут эскалации: off, 1h, 4h, 24h"
    },
    "escalationAutoResolveStrategy": {
      "type": "string",
      "default": null,
      "description": "Стратегия авто-резолва: suggest-edit, reject-default"
    }
  }
}
    arguments 105 lines
  • project-delete unknown never probed

    Delete a project. If the project has goals, pass force=true to cascade-delete them all; without force, the call is rejected with the goals count. Returns deleted title, slug, and goals_deleted count.

    mcp-tool

    {
  "type": "object",
  "required": [
    "projectId"
  ],
  "properties": {
    "force": {
      "type": "boolean",
      "default": null,
      "description": "Удалить вместе со всеми целями (default: false — откажет если есть цели)"
    },
    "projectId": {
      "type": "string",
      "description": "UUID проекта"
    }
  }
}
    arguments 17 lines
  • project-list unknown never probed

    List all projects with optional status filter (active/archived/paused). Returns id, title, slug, webUrl, icon, and goals_count for each project. Use project-get for full details with goals breakdown by status.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "status": {
      "type": "string",
      "default": null,
      "description": "Статус: active / archived / paused"
    }
  }
}
    arguments 10 lines
  • goal-block unknown never probed

    Add a blocker to a goal (blockers are additive — each call appends a new one, existing blockers are preserved). Sets status to blocked. Optionally create an inline resolver goal (resolverTitle) or link an existing one (linkedGoalId) — mutually exclusive. When the last active blocker is removed via goal-remove-blocker, the goal returns to its previous status.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId",
    "description"
  ],
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID блокируемой цели"
    },
    "description": {
      "type": "string",
      "description": "Описание блокера — что мешает"
    },
    "linkedGoalId": {
      "type": "string",
      "default": null,
      "description": "UUID существующей цели-резолвера (взаимоисключающе с resolverTitle)"
    },
    "resolverTitle": {
      "type": "string",
      "default": null,
      "description": "Заголовок новой цели-резолвера (взаимоисключающе с linkedGoalId)"
    },
    "resolverParentId": {
      "type": "string",
      "default": null,
      "description": "UUID родителя резолвера (default = goalId, т.е. дочерняя)"
    },
    "resolverDescription": {
      "type": "string",
      "default": null,
      "description": "Описание цели-резолвера"
    }
  }
}
    arguments 37 lines
  • goal-remove-blocker unknown never probed

    Remove a blocker from a goal by blocker UUID. If it was the last active blocker, the goal automatically returns to its previous status (in_progress or backlog). Does not delete the linked resolver goal if one exists.

    mcp-tool

    {
  "type": "object",
  "required": [
    "goalId",
    "blockerId"
  ],
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "blockerId": {
      "type": "string",
      "description": "UUID блокера"
    }
  }
}
    arguments 17 lines
  • goal-create unknown never probed

    Create a goal/task/milestone/habit in the planning tree. Two modes: grove (default) — enforces acceptance criteria gate on status transitions (AC required before ready_for_work, file-evidence per AC before done); standard — carries the same AC but without the evidence gate (advisory linting only). Returns the created goal with id, webUrl, mode, and nextStep hint. For an explicit visible UI result, the response may include an advisory visualAcSuggestion; adopt its criterion through goal-add-criterion with visualEvidenceSuggested=true, or ignore it. Every goal must belong to a project (pass projectId or inherit from parent).

    mcp-tool

    {
  "type": "object",
  "required": [
    "title"
  ],
  "properties": {
    "mode": {
      "type": "string",
      "default": null,
      "description": "Режим: grove (default) или standard. Grove enforce-ит I_start на ready_for_work и I₃ на done; standard несёт те же AC, но без evidence-гейта"
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "default": null,
      "description": "Теги"
    },
    "type": {
      "type": "string",
      "default": null,
      "description": "goal / milestone / task / habit (default: task)"
    },
    "title": {
      "type": "string",
      "description": "Название цели (макс. 500)"
    },
    "status": {
      "type": "string",
      "default": null,
      "description": "backlog (default) / ready_for_work (объявить контракт готовым; grove в проекте с обязательным red-team объявляется только через goal-update)"
    },
    "deadline": {
      "type": "string",
      "default": null,
      "description": "Дедлайн ISO 8601"
    },
    "estimate": {
      "type": "string",
      "default": null,
      "description": "Оценка"
    },
    "parentId": {
      "type": "string",
      "default": null,
      "description": "UUID родителя (null = root)"
    },
    "priority": {
      "type": "integer",
      "default": null,
      "description": "Приоритет 1–5 (default: 3)"
    },
    "projectId": {
      "type": "string",
      "default": null,
      "description": "UUID проекта"
    },
    "description": {
      "type": "string",
      "default": null,
      "description": "Описание"
    },
    "acceptanceCriteria": {
      "type": "array",
      "items": {},
      "default": null,
      "description": "Список AC: строка (pre-merge критерий) или объект {text, probeClass?: pre-merge|post-deploy, probeSpec?}. post-deploy критерий обязан нести исполнимую пробу probeSpec {method, url, expect:{http_code, body:{field: expectedValue}}} — иначе error=probe_required; probeSpec без probeClass = post-deploy. Grove: опциональны на create, обязательны до объявления ready_for_work, блокирующий quality-линтер. Standard: описательные, линтер advisory"
    }
  }
}
    arguments 71 lines
  • goal-update-criterion unknown never probed

    Update an acceptance criterion: its text and/or its class + probe. probeClass=post-deploy requires an executable probeSpec {method, url, expect:{http_code, body}} (kept from the criterion when omitted and one already exists; otherwise error=probe_required); probeSpec alone implies post-deploy; probeClass=pre-merge drops the probe. Grove mode: only while goal is in backlog (frozen once started), quality linter blocks high-severity issues. Standard mode: until goal is done, linter is advisory. Returns updated criterion details (text, probeClass, probeSpec) and any quality findings.

    mcp-tool

    {
  "type": "object",
  "required": [
    "criterionId"
  ],
  "properties": {
    "text": {
      "type": "string",
      "default": null,
      "description": "New criterion text (omit to keep)"
    },
    "probeSpec": {
      "default": null,
      "properties": {
        "url": {
          "type": "string",
          "description": "Absolute http(s) URL the runner requests on the deployed instance"
        },
        "expect": {
          "type": "object",
          "properties": {
            "body": {
              "type": "object",
              "additionalProperties": true
            },
            "http_code": {
              "type": "integer",
              "maximum": 599,
              "minimum": 100
            }
          },
          "description": "What the response must contain: http_code (exact) and/or body (subset of fields with expected scalar values; nested objects = nested fields; \"{{deployed_revision}}\" = SHA of the revision that triggered the probe)"
        },
        "method": {
          "enum": [
            "GET",
            "HEAD"
          ],
          "type": "string",
          "description": "HTTP method of the probe request"
        }
      },
      "description": "Исполнимая проба post-deploy критерия: {method, url, expect: {http_code, body: {field: expectedValue}}}; \"{{deployed_revision}}\" в ожидаемых значениях = SHA развёрнутой ревизии. Пример: {\"method\":\"GET\",\"url\":\"https://planner.monopoly-gold.com/api/healthz\",\"expect\":{\"http_code\":200,\"body\":{\"status\":\"ok\",\"revision\":\"{{deployed_revision}}\"}}}"
    },
    "probeClass": {
      "enum": [
        "pre-merge",
        "post-deploy",
        null
      ],
      "type": "string",
      "default": null,
      "description": "Класс критерия: pre-merge (доказывается в CI / приложенным evidence; сбрасывает пробу) или post-deploy (доказывается исполнимой пробой против прода; требует probeSpec — свой или уже сохранённый)"
    },
    "criterionId": {
      "type": "string",
      "description": "UUID acceptance criterion"
    }
  }
}
    arguments 60 lines
  • goal-remove-criterion unknown never probed

    Remove an acceptance criterion from a goal. Grove mode: only while goal is in backlog (frozen once started). Standard mode: until goal is done. Cascades to all evidence on the criterion. Returns confirmation with removed criterion details.

    mcp-tool

    {
  "type": "object",
  "required": [
    "criterionId"
  ],
  "properties": {
    "criterionId": {
      "type": "string",
      "description": "UUID acceptance criterion"
    }
  }
}
    arguments 12 lines
  • goal-attach-evidence unknown never probed

    PRIMARY path to close a Grove goal: this is the ONLY tool that covers an acceptance criterion. Attach binary evidence (screenshot, log dump, API response, export) to an AC — call it once per criterion to satisfy the close gate. The subordinate goal-add-evidence-text only adds context for proofs with NO bytes (URLs to permanent external sources, manual repro descriptions) and does NOT cover an AC. Caption is optional but strongly recommended: state what the file captures and the reproduction conditions (URL/commit/session/inputs) so a third reviewer can reproduce. ⚠ PICK THE RIGHT TRANSPORT BEFORE YOU CALL THIS TOOL ⚠ • BEST for ANY file > ~1 KB raw — and the ONLY no-token path, so use it in a claude.ai / hosted-agent session that has no raw X-Auth-Token → call the sibling MCP tool `goal-request-upload` with this same criterionId. It returns a one-time {uploadUrl, expiresAt}; then stream the raw bytes with a single PUT: `curl -sS --fail --upload-file "/abs/path/to/file.png" "<uploadUrl>"` (optionally add -H "X-Content-Sha256: <hex sha256>" so corruption fails fast). No base64, no token — the signed ?t= ticket in the URL is the only credential, single-use, criterion-scoped. The PUT response is the same evidence JSON this tool returns. • ALTERNATIVELY, if you DO have the raw X-Auth-Token in your shell → the `planner-attach.sh` helper (zero-install bash, binary-safe). The MCP base64 path below is unreliable for non-trivial files: long string arguments get truncated or whitespace-corrupted on the agent side BEFORE the JSON-RPC request is sent. Measured 2026-05-20 on prod: a 4 KB PNG arrived at the server as 1874 decoded bytes (file_hash_mismatch); a 2 KB payload arrived with stray whitespace (failed base64_decode). The server itself accepts up to 25 MiB raw — the bottleneck is the agent-side serialisation of contentBase64, NOT the server. planner-attach.sh COPY-PASTE RECIPE (replace 3 placeholders, run in your shell): curl -sS https://planner.monopoly-gold.com/api/cli/planner-attach.sh \ | PLANNER_TOKEN="<same X-Auth-Token you use for MCP>" bash -s -- \ --criterion-id "<CRITERION_UUID>" \ --file "/abs/path/to/file.png" \ --caption "what is captured and the repro conditions" \ --created-by "<your agent id>" Where to get each value: - PLANNER_TOKEN: the very same token that is already in your MCP config under the X-Auth-Token header for the `planner` server. NOT a separate credential. - CRITERION_UUID: the AC id you got from goal-get / goal-list. Same UUID you would pass to this MCP tool. - file path: absolute path on YOUR (agent) machine — the script reads it locally and streams multipart. The planner server never sees your filesystem. The helper computes SHA-256 itself and ships it as `contentSha256`, so any in-flight corruption fails fast with HTTP 400 instead of poisoning the evidence row. Output on stdout is the same JSON shape this MCP tool returns; non-zero exit means HTTP ≥ 400 (stderr explains). Without curl/bash? Fall back to raw multipart: POST https://planner.monopoly-gold.com/api/criteria/<id>/evidence/file, header X-Auth-Token, form fields file=@..., contentSha256=..., caption, createdBy. • File ≤ ~1 KB raw → this MCP tool is fine. ALWAYS pass `contentSha256` (hex SHA-256 of raw bytes BEFORE base64). Without it, a silently truncated PNG looks valid to the MIME sniffer; the server cannot distinguish a truncated 4 KB PNG from a valid 1 KB one and the vision judge burns ~30s on broken bytes. With the hash, the server fast-fails with error=file_hash_mismatch and points back here at the multipart endpoint. Validates MIME whitelist (png/jpeg/webp/gif/mp4/pdf/txt/json/zip), per-file size cap (ATTACHMENTS_MAX_FILE_BYTES, default 25 MiB), per-project attachments quota. Returns evidence record + file URL + serverSha256.

    mcp-tool

    {
  "type": "object",
  "required": [
    "criterionId",
    "filename",
    "contentBase64"
  ],
  "properties": {
    "kind": {
      "type": "string",
      "default": null,
      "description": "Optional evidence kind override. The only accepted value is `session_history` —\nmarks this attachment as the goal-level «full Claude session transcript» artifact\nrequired by the close gate (I4-session-history). Such evidence does NOT cover any AC\nand is NOT sent to the evidence judge. Omit for normal per-AC proof (kind is derived\nfrom MIME). NOTE: transcripts are usually > 1 KB → use goal-request-upload\n(pass kind=session_history) or the multipart helper, not this base64 path."
    },
    "caption": {
      "type": "string",
      "default": null,
      "description": "Optional human-readable description, stored in evidence.payload"
    },
    "filename": {
      "type": "string",
      "description": "Original filename (used to derive MIME). Path components are stripped."
    },
    "mimeType": {
      "type": "string",
      "default": null,
      "description": "MIME type — if omitted, derived from filename extension; must be in whitelist"
    },
    "createdBy": {
      "type": "string",
      "default": null,
      "description": "Identifier of the uploading agent"
    },
    "criterionId": {
      "type": "string",
      "description": "UUID acceptance criterion the file will be evidence for"
    },
    "contentBase64": {
      "type": "string",
      "description": "File payload, base64-encoded (RFC 4648 §4 standard alphabet, padding optional)"
    },
    "contentSha256": {
      "type": "string",
      "default": null,
      "description": "Hex-encoded SHA-256 of the raw bytes (before base64). When provided, the server\nrecomputes the hash on the decoded payload and rejects with error=file_hash_mismatch\nif they diverge — primary defence against MCP base64 truncation."
    }
  }
}
    arguments 47 lines
  • goal-request-upload unknown never probed

    PREFERRED path to attach a LARGE binary evidence file (screenshot, log dump, PDF, session transcript — anything > ~1 KB) to an acceptance criterion. Returns a one-time {uploadUrl, expiresAt} scoped to this criterion. Then STREAM the raw file to it with a single PUT — no base64, no token: curl -sS --fail --upload-file "/abs/path/to/file.png" "<uploadUrl>" Optionally pass the hex SHA-256 of the file so the server fast-fails on any in-flight corruption: curl -sS --fail -H "X-Content-Sha256: <sha256>" --upload-file "/abs/path/to/file.png" "<uploadUrl>" The PUT response is the same evidence JSON that goal-attach-evidence returns (evidence id, serverSha256, judge verdict, criterion evidenceCount). A non-2xx PUT means the upload was rejected (expired/already-used/wrong-criterion/hash-mismatch) and NO evidence was created — request a fresh URL and retry. Use this instead of goal-attach-evidence for any non-trivial file. Use goal-add-evidence-text only for byte-less context (external URLs, manual repro notes) — it does NOT cover an AC. GOAL ATTACHMENTS (description illustrations, NOT evidence): pass goalId INSTEAD of criterionId. The PUT then creates a goal attachment and returns {attachment.url, attachment.markdown} — paste `markdown` into the goal description and the web UI renders images inline. Such a file is not bound to any AC and never counts toward closing the goal.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "default": null,
      "description": "Optional evidence kind override. Only accepted value is\n`session_history` (goal-level transcript artifact; does NOT cover an AC)."
    },
    "goalId": {
      "type": "string",
      "default": null,
      "description": "UUID of a goal — issues a ticket for a DESCRIPTION ATTACHMENT (not evidence); mutually exclusive with criterionId"
    },
    "caption": {
      "type": "string",
      "default": null,
      "description": "Optional human-readable description, stored on the evidence"
    },
    "createdBy": {
      "type": "string",
      "default": null,
      "description": "Identifier of the uploading agent"
    },
    "criterionId": {
      "type": "string",
      "default": null,
      "description": "UUID acceptance criterion the file will be evidence for (omit when goalId is given)"
    }
  }
}
    arguments 30 lines
  • goal-add-evidence-text unknown never probed

    SUBORDINATE / supplementary path — does NOT close an acceptance criterion. Adds a text-only note (URL to a permanent external source like CI run / GitHub commit / issue, or a description of a manual scenario) as extra context alongside the real proof. The path that actually covers an AC and closes a Grove goal is goal-attach-evidence — use that one for every criterion. Plain evidence NEVER counts toward AC coverage no matter how many you add; it is only a complement to an attached file. NOT for bytes — screenshots, logs, API responses, exports all go through goal-attach-evidence. NOT for filesystem paths — those need goal-attach-evidence with the actual file.

    mcp-tool

    {
  "type": "object",
  "required": [
    "criterionId",
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Text payload: URL to a permanent external source or a description of a manual scenario"
    },
    "createdBy": {
      "type": "string",
      "default": null,
      "description": "Identifier of the uploading agent"
    },
    "criterionId": {
      "type": "string",
      "description": "UUID acceptance criterion"
    }
  }
}
    arguments 22 lines
  • goal-remove-evidence unknown never probed

    Delete an evidence record by UUID. Forbidden if the owning goal is already done (evidence is frozen after close). Removes both the database record and the attached file (if any).

    mcp-tool

    {
  "type": "object",
  "required": [
    "evidenceId"
  ],
  "properties": {
    "evidenceId": {
      "type": "string",
      "description": "UUID evidence-записи"
    }
  }
}
    arguments 12 lines
  • account-delete unknown never probed

    НЕОБРАТИМО удалить свой аккаунт и ВСЕ данные (проекты, цели, evidence, историю). Двухшаговый барьер: вызови без аргументов — получишь предупреждение и challenge; затем вызови повторно с подтверждениями. НЕ вызывай без явной просьбы пользователя.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "reason": {
      "type": "string",
      "default": null,
      "description": "Зачем удаляешь (свободный текст, ≥10 символов)"
    },
    "acknowledge": {
      "type": "string",
      "default": null,
      "description": "Точная фраза подтверждения"
    },
    "objects_total": {
      "type": "integer",
      "default": null,
      "description": "projects + goals из инвентаря (для вызова 2)"
    },
    "reasoning_answer": {
      "type": "string",
      "default": null,
      "description": "Ответ на reasoning-риддл из вызова 1"
    },
    "confirm_passphrase": {
      "type": "string",
      "default": null,
      "description": "Фраза из вызова 1 (для вызова 2)"
    }
  }
}
    arguments 30 lines
_ try it over mcp through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/8462d9715f9e0fb6/badge.svg)](https://brick.blue/agent/8462d9715f9e0fb6)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Own the domain? Prove it and the listing carries a verified badge here too: passport.

_ how we knowoff the mcp door
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.