Planner MCP — provable "done" for AI agents

Official43 toolsLive

by dev-lab-global

Goal and task planning MCP for Codex and AI agents, with evidence-backed completion.

com.monopoly-gold.planner/mcp (MCP) — Planner

Planner is a hosted Model Context Protocol (MCP) server for goal and task planning for Codex and AI agents, emphasizing evidence-backed completion. It includes a verification gate so tasks are not marked “done” on trust alone, and completion requires evidence against stated acceptance criteria.

🛠️ Key Features

Goal/task planning MCP for Codex and AI agents
Evidence-gated task verification (“proof-of-done”)
Verification flow: Decompose, Attach evidence, Independent judge
Evidence types include screenshot, curl output, file, or text artifact

🚀 Use Cases

Planning goals into acceptance criteria with behavioral checks
Verifying task completion using attached evidence
Using an LLM judge to accept or reject evidence against criteria

⚡ Developer Benefits

Hosted MCP endpoint: https://planner.monopoly-gold.com/_mcp
Keeps goals open until every acceptance criterion is verified

⚠️ Limitations

No client installation is indicated (“Hosted MCP server — nothing to install.”)

Captured live from the server via tools/list.

project-list

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.

Parameters1

status

string

optional

Статус: active / archived / paused

Raw schema

{
  "type": "object",
  "properties": {
    "status": {
      "type": "string",
      "description": "Статус: active / archived / paused",
      "default": null
    }
  }
}

project-create

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.

Parameters10

title	string	required	Название проекта
slug	string	required	Уникальный slug (только a-z, 0-9, дефис)
description	string	optional	Описание проекта
status	string	optional	Статус: active / archived / paused (default: active)
tags	array	optional	Теги
icon	string	optional	Иконка (эмодзи, макс. 10 символов)
repositoryPath	string	optional	Путь к репозиторию на сервере
repositoryUrl	string	optional	URL репозитория
sourceRef	object	optional	Источник кода для remote-research: {type:"git",url,ref}
isDefault	boolean	optional	Сделать проектом по умолчанию

Raw schema

{
  "type": "object",
  "properties": {
    "title": {
      "type": "string",
      "description": "Название проекта"
    },
    "slug": {
      "type": "string",
      "description": "Уникальный slug (только a-z, 0-9, дефис)"
    },
    "description": {
      "type": "string",
      "description": "Описание проекта",
      "default": null
    },
    "status": {
      "type": "string",
      "description": "Статус: active / archived / paused (default: active)",
      "default": null
    },
    "tags": {
      "type": "array",
      "description": "Теги",
      "default": null,
      "items": {
        "type": "string"
      }
    },
    "icon": {
      "type": "string",
      "description": "Иконка (эмодзи, макс. 10 символов)",
      "default": null
    },
    "repositoryPath": {
      "type": "string",
      "description": "Путь к репозиторию на сервере",
      "default": null
    },
    "repositoryUrl": {
      "type": "string",
      "description": "URL репозитория",
      "default": null
    },
    "sourceRef": {
      "type": "object",
      "description": "Источник кода для remote-research: {type:\"git\",url,ref}",
      "default": null
    },
    "isDefault": {
      "type": "boolean",
      "description": "Сделать проектом по умолчанию",
      "default": null
    }
  },
  "required": [
    "title",
    "slug"
  ]
}

project-get

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.

Parameters1

projectId

string

required

UUID проекта

Raw schema

{
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "description": "UUID проекта"
    }
  },
  "required": [
    "projectId"
  ]
}

project-update

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.

Parameters19

projectId	string	required	UUID проекта
title	string	optional	Новое название
slug	string	optional	Новый slug (только a-z, 0-9, дефис; должен быть уникальным)
description	string	optional	Новое описание
status	string	optional	Новый статус: active, archived, paused
tags	array	optional	Новые теги
icon	string	optional	Иконка (эмодзи, макс. 10 символов)
repositoryPath	string	optional	Путь к репозиторию на сервере
repositoryUrl	string	optional	URL репозитория
sourceRef	object	optional	Источник кода для remote-research: {type:"git",url,ref}
clearSourceRef	boolean	optional	Установить sourceRef в null (отвязать репозиторий); несовместим с sourceRef
isDefault	boolean	optional	Сделать проектом по умолчанию
redTeamMode	string	optional	Режим red-team: optional, advisory, required
evidenceJudgeMode	string	optional	Режим судьи доказательств: off, optional, required
allowedGoalMode	string	optional	Разрешённые режимы целей: any, grove_only
fmeaGenerationMode	string	optional	FMEA-генерация: off, on
escalationResolveTimeout	string	optional	Таймаут эскалации: off, 1h, 4h, 24h
escalationAutoResolveBy	string	optional	Авто-резолвер эскалации: none, planner-agent
escalationAutoResolveStrategy	string	optional	Стратегия авто-резолва: suggest-edit, reject-default

Raw schema

{
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "description": "UUID проекта"
    },
    "title": {
      "type": "string",
      "description": "Новое название",
      "default": null
    },
    "slug": {
      "type": "string",
      "description": "Новый slug (только a-z, 0-9, дефис; должен быть уникальным)",
      "default": null
    },
    "description": {
      "type": "string",
      "description": "Новое описание",
      "default": null
    },
    "status": {
      "type": "string",
      "description": "Новый статус: active, archived, paused",
      "default": null
    },
    "tags": {
      "type": "array",
      "description": "Новые теги",
      "default": null,
      "items": {
        "type": "string"
      }
    },
    "icon": {
      "type": "string",
      "description": "Иконка (эмодзи, макс. 10 символов)",
      "default": null
    },
    "repositoryPath": {
      "type": "string",
      "description": "Путь к репозиторию на сервере",
      "default": null
    },
    "repositoryUrl": {
      "type": "string",
      "description": "URL репозитория",
      "default": null
    },
    "sourceRef": {
      "type": "object",
      "description": "Источник кода для remote-research: {type:\"git\",url,ref}",
      "default": null
    },
    "clearSourceRef": {
      "type": "boolean",
      "description": "Установить sourceRef в null (отвязать репозиторий); несовместим с sourceRef",
      "default": null
    },
    "isDefault": {
      "type": "boolean",
      "description": "Сделать проектом по умолчанию",
      "default": null
    },
    "redTeamMode": {
      "type": "string",
      "description": "Режим red-team: optional, advisory, required",
      "default": null
    },
    "evidenceJudgeMode": {
      "type": "string",
      "description": "Режим судьи доказательств: off, optional, required",
      "default": null
    },
    "allowedGoalMode": {
      "type": "string",
      "description": "Разрешённые режимы целей: any, grove_only",
      "default": null
    },
    "fmeaGenerationMode": {
      "type": "string",
      "description": "FMEA-генерация: off, on",
      "default": null
    },
    "escalationResolveTimeout": {
      "type": "string",
      "description": "Таймаут эскалации: off, 1h, 4h, 24h",
      "default": null
    },
    "escalationAutoResolveBy": {
      "type": "string",
      "description": "Авто-резолвер эскалации: none, planner-agent",
      "default": null
    },
    "escalationAutoResolveStrategy": {
      "type": "string",
      "description": "Стратегия авто-резолва: suggest-edit, reject-default",
      "default": null
    }
  },
  "required": [
    "projectId"
  ]
}

project-delete

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.

Parameters2

projectId	string	required	UUID проекта
force	boolean	optional	Удалить вместе со всеми целями (default: false — откажет если есть цели)

Raw schema

{
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "description": "UUID проекта"
    },
    "force": {
      "type": "boolean",
      "description": "Удалить вместе со всеми целями (default: false — откажет если есть цели)",
      "default": null
    }
  },
  "required": [
    "projectId"
  ]
}

project-add-dependency

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.

Parameters2

projectId	string	required	UUID или slug проекта-зависимого
dependsOnProjectId	string	required	UUID или slug проекта, от которого зависит

Raw schema

{
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "description": "UUID или slug проекта-зависимого"
    },
    "dependsOnProjectId": {
      "type": "string",
      "description": "UUID или slug проекта, от которого зависит"
    }
  },
  "required": [
    "projectId",
    "dependsOnProjectId"
  ]
}

project-remove-dependency

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.

Parameters3

dependencyId	string	optional	UUID самой связи
projectId	string	optional	UUID или slug проекта-зависимого (если dependencyId не задан)
dependsOnProjectId	string	optional	UUID или slug целевого проекта (если dependencyId не задан)

Raw schema

{
  "type": "object",
  "properties": {
    "dependencyId": {
      "type": "string",
      "description": "UUID самой связи",
      "default": null
    },
    "projectId": {
      "type": "string",
      "description": "UUID или slug проекта-зависимого (если dependencyId не задан)",
      "default": null
    },
    "dependsOnProjectId": {
      "type": "string",
      "description": "UUID или slug целевого проекта (если dependencyId не задан)",
      "default": null
    }
  }
}

goal-list

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.

Parameters5

projectId	string	optional	UUID проекта (фильтр)
status	string	optional	Статус: backlog, checking_ac, checking_ac_failed, checking_ac_errored, ready_for_work, in_progress, blocked, done, cancelled
type	string	optional	Тип: goal, milestone, task, habit
parentId	string	optional	UUID родителя (только прямые дети)
limit	integer	optional	Макс. кол-во результатов (default: 50)

Raw schema

{
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "description": "UUID проекта (фильтр)",
      "default": null
    },
    "status": {
      "type": "string",
      "description": "Статус: backlog, checking_ac, checking_ac_failed, checking_ac_errored, ready_for_work, in_progress, blocked, done, cancelled",
      "default": null
    },
    "type": {
      "type": "string",
      "description": "Тип: goal, milestone, task, habit",
      "default": null
    },
    "parentId": {
      "type": "string",
      "description": "UUID родителя (только прямые дети)",
      "default": null
    },
    "limit": {
      "type": "integer",
      "description": "Макс. кол-во результатов (default: 50)",
      "default": null
    }
  }
}

goal-create

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).

Parameters12

title	string	required	Название цели (макс. 500)
parentId	string	optional	UUID родителя (null = root)
projectId	string	optional	UUID проекта
type	string	optional	goal / milestone / task / habit (default: task)
status	string	optional	backlog (default) / ready_for_work (объявить контракт готовым; grove в проекте с обязательным red-team объявляется только через goal-update)
priority	integer	optional	Приоритет 1–5 (default: 3)
description	string	optional	Описание
tags	array	optional	Теги
deadline	string	optional	Дедлайн ISO 8601
estimate	string	optional	Оценка
mode	string	optional	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
acceptanceCriteria	array	optional	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

Raw schema

{
  "type": "object",
  "properties": {
    "title": {
      "type": "string",
      "description": "Название цели (макс. 500)"
    },
    "parentId": {
      "type": "string",
      "description": "UUID родителя (null = root)",
      "default": null
    },
    "projectId": {
      "type": "string",
      "description": "UUID проекта",
      "default": null
    },
    "type": {
      "type": "string",
      "description": "goal / milestone / task / habit (default: task)",
      "default": null
    },
    "status": {
      "type": "string",
      "description": "backlog (default) / ready_for_work (объявить контракт готовым; grove в проекте с обязательным red-team объявляется только через goal-update)",
      "default": null
    },
    "priority": {
      "type": "integer",
      "description": "Приоритет 1–5 (default: 3)",
      "default": null
    },
    "description": {
      "type": "string",
      "description": "Описание",
      "default": null
    },
    "tags": {
      "type": "array",
      "description": "Теги",
      "default": null,
      "items": {
        "type": "string"
      }
    },
    "deadline": {
      "type": "string",
      "description": "Дедлайн ISO 8601",
      "default": null
    },
    "estimate": {
      "type": "string",
      "description": "Оценка",
      "default": null
    },
    "mode": {
      "type": "string",
      "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",
      "default": null
    },
    "acceptanceCriteria": {
      "type": "array",
      "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",
      "default": null,
      "items": {}
    }
  },
  "required": [
    "title"
  ]
}

goal-get

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.

Parameters1

goalId

string

required

UUID цели

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    }
  },
  "required": [
    "goalId"
  ]
}

goal-update

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. backlog→in_progress and backlog→done are rejected. Returns the updated goal with all fields.

Parameters12

goalId	string	required	UUID цели
title	string	optional	Новое название (макс. 500)
status	string	optional	Новый статус: backlog, ready_for_work, in_progress, blocked, done, cancelled (checking_ac* выставляет система)
priority	integer	optional	Новый приоритет (1–5)
description	string	optional	Новое описание
type	string	optional	Новый тип: goal, milestone, task, habit
tags	array	optional	Новые теги
deadline	string	optional	Новый дедлайн (ISO 8601)
estimate	string	optional	Новая оценка
mode	string	optional	Режим цели: standard или grove. Иммутабелен после mode_locked_at
attemptCommit	string	optional	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	boolean	optional	Отклонить advisory visual-AC; для ready_for_work это явный выбор «продолжить без предложения»

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "title": {
      "type": "string",
      "description": "Новое название (макс. 500)",
      "default": null
    },
    "status": {
      "type": "string",
      "description": "Новый статус: backlog, ready_for_work, in_progress, blocked, done, cancelled (checking_ac* выставляет система)",
      "default": null
    },
    "priority": {
      "type": "integer",
      "description": "Новый приоритет (1–5)",
      "default": null
    },
    "description": {
      "type": "string",
      "description": "Новое описание",
      "default": null
    },
    "type": {
      "type": "string",
      "description": "Новый тип: goal, milestone, task, habit",
      "default": null
    },
    "tags": {
      "type": "array",
      "description": "Новые теги",
      "default": null,
      "items": {
        "type": "string"
      }
    },
    "deadline": {
      "type": "string",
      "description": "Новый дедлайн (ISO 8601)",
      "default": null
    },
    "estimate": {
      "type": "string",
      "description": "Новая оценка",
      "default": null
    },
    "mode": {
      "type": "string",
      "description": "Режим цели: standard или grove. Иммутабелен после mode_locked_at",
      "default": null
    },
    "attemptCommit": {
      "type": "string",
      "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",
      "default": null
    },
    "dismissVisualAcSuggestion": {
      "type": "boolean",
      "description": "Отклонить advisory visual-AC; для ready_for_work это явный выбор «продолжить без предложения»",
      "default": null
    }
  },
  "required": [
    "goalId"
  ]
}

goal-delete

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.

Parameters1

goalId

string

required

UUID цели

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    }
  },
  "required": [
    "goalId"
  ]
}

goal-move

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.

Parameters3

goalId	string	required	UUID перемещаемой цели
newParentId	string	optional	UUID нового родителя (null = сделать root)
projectId	string	optional	UUID целевого проекта (используется при newParentId=null для cross-project move в корень)

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID перемещаемой цели"
    },
    "newParentId": {
      "type": "string",
      "description": "UUID нового родителя (null = сделать root)",
      "default": null
    },
    "projectId": {
      "type": "string",
      "description": "UUID целевого проекта (используется при newParentId=null для cross-project move в корень)",
      "default": null
    }
  },
  "required": [
    "goalId"
  ]
}

goal-reorder

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.

Parameters1

ids

array

required

UUID целей в новом порядке (все должны иметь одного родителя и одинаковый priority)

Raw schema

{
  "type": "object",
  "properties": {
    "ids": {
      "type": "array",
      "description": "UUID целей в новом порядке (все должны иметь одного родителя и одинаковый priority)",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "ids"
  ]
}

goal-block

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.

Parameters6

goalId	string	required	UUID блокируемой цели
description	string	required	Описание блокера — что мешает
linkedGoalId	string	optional	UUID существующей цели-резолвера (взаимоисключающе с resolverTitle)
resolverTitle	string	optional	Заголовок новой цели-резолвера (взаимоисключающе с linkedGoalId)
resolverParentId	string	optional	UUID родителя резолвера (default = goalId, т.е. дочерняя)
resolverDescription	string	optional	Описание цели-резолвера

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID блокируемой цели"
    },
    "description": {
      "type": "string",
      "description": "Описание блокера — что мешает"
    },
    "linkedGoalId": {
      "type": "string",
      "description": "UUID существующей цели-резолвера (взаимоисключающе с resolverTitle)",
      "default": null
    },
    "resolverTitle": {
      "type": "string",
      "description": "Заголовок новой цели-резолвера (взаимоисключающе с linkedGoalId)",
      "default": null
    },
    "resolverParentId": {
      "type": "string",
      "description": "UUID родителя резолвера (default = goalId, т.е. дочерняя)",
      "default": null
    },
    "resolverDescription": {
      "type": "string",
      "description": "Описание цели-резолвера",
      "default": null
    }
  },
  "required": [
    "goalId",
    "description"
  ]
}

goal-remove-blocker

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.

Parameters2

goalId	string	required	UUID цели
blockerId	string	required	UUID блокера

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "blockerId": {
      "type": "string",
      "description": "UUID блокера"
    }
  },
  "required": [
    "goalId",
    "blockerId"
  ]
}

goal-todo

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.

Parameters5

title	string	required	Название задачи
description	string	optional	Описание
project	string	optional	Slug проекта (если не указан — используется дефолтный)
priority	integer	optional	Приоритет 1–5 (default: 4)
tags	array	optional	Теги (автоматически добавляется "suggestion")

Raw schema

{
  "type": "object",
  "properties": {
    "title": {
      "type": "string",
      "description": "Название задачи"
    },
    "description": {
      "type": "string",
      "description": "Описание",
      "default": null
    },
    "project": {
      "type": "string",
      "description": "Slug проекта (если не указан — используется дефолтный)",
      "default": null
    },
    "priority": {
      "type": "integer",
      "description": "Приоритет 1–5 (default: 4)",
      "default": null
    },
    "tags": {
      "type": "array",
      "description": "Теги (автоматически добавляется \"suggestion\")",
      "default": null,
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "title"
  ]
}

goal-add-note

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[].

Parameters2

goalId	string	required	UUID цели
text	string	required	Текст заметки (markdown)

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "text": {
      "type": "string",
      "description": "Текст заметки (markdown)"
    }
  },
  "required": [
    "goalId",
    "text"
  ]
}

goal-remove-note

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.

Parameters2

goalId	string	required	UUID цели
noteId	string	required	UUID заметки

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "noteId": {
      "type": "string",
      "description": "UUID заметки"
    }
  },
  "required": [
    "goalId",
    "noteId"
  ]
}

goal-tree

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.

Parameters2

projectId	string	optional	UUID проекта (по умолчанию: все проекты)
rootId	string	optional	UUID корня поддерева

Raw schema

{
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "description": "UUID проекта (по умолчанию: все проекты)",
      "default": null
    },
    "rootId": {
      "type": "string",
      "description": "UUID корня поддерева",
      "default": null
    }
  }
}

goal-summary

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.

Parameters1

projectId

string

optional

UUID проекта

Raw schema

{
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "description": "UUID проекта",
      "default": null
    }
  }
}

goal-add-criterion

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.

Parameters6

goalId	string	required	UUID цели
text	string	required	Формулировка критерия
position	integer	optional	Позиция (default = append в конец)
probeClass	string	optional	Класс критерия: pre-merge (default; доказывается в CI / приложенным evidence) или post-deploy (доказывается исполнимой пробой против прода; требует probeSpec)
probeSpec	any	optional	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}}"}}}
visualEvidenceSuggested	boolean	optional	True only when this AC accepts Planner's visual-AC advisory

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "text": {
      "type": "string",
      "description": "Формулировка критерия"
    },
    "position": {
      "type": "integer",
      "description": "Позиция (default = append в конец)",
      "default": null
    },
    "probeClass": {
      "type": "string",
      "description": "Класс критерия: pre-merge (default; доказывается в CI / приложенным evidence) или post-deploy (доказывается исполнимой пробой против прода; требует probeSpec)",
      "default": null,
      "enum": [
        "pre-merge",
        "post-deploy",
        null
      ]
    },
    "probeSpec": {
      "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}}\"}}}",
      "default": null,
      "properties": {
        "method": {
          "type": "string",
          "enum": [
            "GET",
            "HEAD"
          ],
          "description": "HTTP method of the probe request"
        },
        "url": {
          "type": "string",
          "description": "Absolute http(s) URL the runner requests on the deployed instance"
        },
        "expect": {
          "type": "object",
          "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)",
          "properties": {
            "http_code": {
              "type": "integer",
              "minimum": 100,
              "maximum": 599
            },
            "body": {
              "type": "object",
              "additionalProperties": true
            }
          }
        }
      }
    },
    "visualEvidenceSuggested": {
      "type": "boolean",
      "description": "True only when this AC accepts Planner's visual-AC advisory",
      "default": false
    }
  },
  "required": [
    "goalId",
    "text"
  ]
}

goal-update-criterion

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.

Parameters4

criterionId	string	required	UUID acceptance criterion
text	string	optional	New criterion text (omit to keep)
probeClass	string	optional	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)
probeSpec	any	optional	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}}"}}}

Raw schema

{
  "type": "object",
  "properties": {
    "criterionId": {
      "type": "string",
      "description": "UUID acceptance criterion"
    },
    "text": {
      "type": "string",
      "description": "New criterion text (omit to keep)",
      "default": null
    },
    "probeClass": {
      "type": "string",
      "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)",
      "default": null,
      "enum": [
        "pre-merge",
        "post-deploy",
        null
      ]
    },
    "probeSpec": {
      "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}}\"}}}",
      "default": null,
      "properties": {
        "method": {
          "type": "string",
          "enum": [
            "GET",
            "HEAD"
          ],
          "description": "HTTP method of the probe request"
        },
        "url": {
          "type": "string",
          "description": "Absolute http(s) URL the runner requests on the deployed instance"
        },
        "expect": {
          "type": "object",
          "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)",
          "properties": {
            "http_code": {
              "type": "integer",
              "minimum": 100,
              "maximum": 599
            },
            "body": {
              "type": "object",
              "additionalProperties": true
            }
          }
        }
      }
    }
  },
  "required": [
    "criterionId"
  ]
}

goal-remove-criterion

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.

Parameters1

criterionId

string

required

UUID acceptance criterion

Raw schema

{
  "type": "object",
  "properties": {
    "criterionId": {
      "type": "string",
      "description": "UUID acceptance criterion"
    }
  },
  "required": [
    "criterionId"
  ]
}

goal-attach-evidence

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.

Parameters8

criterionId	string	required	UUID acceptance criterion the file will be evidence for
filename	string	required	Original filename (used to derive MIME). Path components are stripped.
contentBase64	string	required	File payload, base64-encoded (RFC 4648 §4 standard alphabet, padding optional)
mimeType	string	optional	MIME type — if omitted, derived from filename extension; must be in whitelist
caption	string	optional	Optional human-readable description, stored in evidence.payload
createdBy	string	optional	Identifier of the uploading agent
contentSha256	string	optional	Hex-encoded SHA-256 of the raw bytes (before base64). When provided, the server recomputes the hash on the decoded payload and rejects with error=file_hash_mismatch if they diverge — primary defence against MCP base64 truncation.
kind	string	optional	Optional evidence kind override. The only accepted value is `session_history` — marks this attachment as the goal-level «full Claude session transcript» artifact required by the close gate (I4-session-history). Such evidence does NOT cover any AC and is NOT sent to the evidence judge. Omit for normal per-AC proof (kind is derived from MIME). NOTE: transcripts are usually > 1 KB → use goal-request-upload (pass kind=session_history) or the multipart helper, not this base64 path.

Raw schema

{
  "type": "object",
  "properties": {
    "criterionId": {
      "type": "string",
      "description": "UUID acceptance criterion the file will be evidence for"
    },
    "filename": {
      "type": "string",
      "description": "Original filename (used to derive MIME). Path components are stripped."
    },
    "contentBase64": {
      "type": "string",
      "description": "File payload, base64-encoded (RFC 4648 §4 standard alphabet, padding optional)"
    },
    "mimeType": {
      "type": "string",
      "description": "MIME type — if omitted, derived from filename extension; must be in whitelist",
      "default": null
    },
    "caption": {
      "type": "string",
      "description": "Optional human-readable description, stored in evidence.payload",
      "default": null
    },
    "createdBy": {
      "type": "string",
      "description": "Identifier of the uploading agent",
      "default": null
    },
    "contentSha256": {
      "type": "string",
      "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.",
      "default": null
    },
    "kind": {
      "type": "string",
      "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.",
      "default": null
    }
  },
  "required": [
    "criterionId",
    "filename",
    "contentBase64"
  ]
}

goal-request-upload

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.

Parameters5

criterionId	string	optional	UUID acceptance criterion the file will be evidence for (omit when goalId is given)
caption	string	optional	Optional human-readable description, stored on the evidence
createdBy	string	optional	Identifier of the uploading agent
kind	string	optional	Optional evidence kind override. Only accepted value is `session_history` (goal-level transcript artifact; does NOT cover an AC).
goalId	string	optional	UUID of a goal — issues a ticket for a DESCRIPTION ATTACHMENT (not evidence); mutually exclusive with criterionId

Raw schema

{
  "type": "object",
  "properties": {
    "criterionId": {
      "type": "string",
      "description": "UUID acceptance criterion the file will be evidence for (omit when goalId is given)",
      "default": null
    },
    "caption": {
      "type": "string",
      "description": "Optional human-readable description, stored on the evidence",
      "default": null
    },
    "createdBy": {
      "type": "string",
      "description": "Identifier of the uploading agent",
      "default": null
    },
    "kind": {
      "type": "string",
      "description": "Optional evidence kind override. Only accepted value is\n`session_history` (goal-level transcript artifact; does NOT cover an AC).",
      "default": null
    },
    "goalId": {
      "type": "string",
      "description": "UUID of a goal — issues a ticket for a DESCRIPTION ATTACHMENT (not evidence); mutually exclusive with criterionId",
      "default": null
    }
  }
}

goal-add-evidence-text

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.

Parameters3

criterionId	string	required	UUID acceptance criterion
text	string	required	Text payload: URL to a permanent external source or a description of a manual scenario
createdBy	string	optional	Identifier of the uploading agent

Raw schema

{
  "type": "object",
  "properties": {
    "criterionId": {
      "type": "string",
      "description": "UUID acceptance criterion"
    },
    "text": {
      "type": "string",
      "description": "Text payload: URL to a permanent external source or a description of a manual scenario"
    },
    "createdBy": {
      "type": "string",
      "description": "Identifier of the uploading agent",
      "default": null
    }
  },
  "required": [
    "criterionId",
    "text"
  ]
}

goal-remove-evidence

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).

Parameters1

evidenceId

string

required

UUID evidence-записи

Raw schema

{
  "type": "object",
  "properties": {
    "evidenceId": {
      "type": "string",
      "description": "UUID evidence-записи"
    }
  },
  "required": [
    "evidenceId"
  ]
}

goal-add-assumption

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.

Parameters3

goalId	string	required	UUID цели (ребёнка — assumption живёт на ребре parent→child)
text	string	required	Формулировка допущения
signpost	string	optional	Наблюдаемый индикатор провала (опционально)

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели (ребёнка — assumption живёт на ребре parent→child)"
    },
    "text": {
      "type": "string",
      "description": "Формулировка допущения"
    },
    "signpost": {
      "type": "string",
      "description": "Наблюдаемый индикатор провала (опционально)",
      "default": null
    }
  },
  "required": [
    "goalId",
    "text"
  ]
}

goal-update-assumption

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

Parameters3

assumptionId	string	required	UUID допущения
text	string	optional	Новый текст допущения
signpost	string	optional	Новый индикатор провала

Raw schema

{
  "type": "object",
  "properties": {
    "assumptionId": {
      "type": "string",
      "description": "UUID допущения"
    },
    "text": {
      "type": "string",
      "description": "Новый текст допущения",
      "default": null
    },
    "signpost": {
      "type": "string",
      "description": "Новый индикатор провала",
      "default": null
    }
  },
  "required": [
    "assumptionId"
  ]
}

goal-remove-assumption

Remove an assumption from a goal edge.

Parameters1

assumptionId

string

required

UUID допущения

Raw schema

{
  "type": "object",
  "properties": {
    "assumptionId": {
      "type": "string",
      "description": "UUID допущения"
    }
  },
  "required": [
    "assumptionId"
  ]
}

goal-suggest-assumptions

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.

Parameters1

goalId

string

required

UUID цели (ребёнка)

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели (ребёнка)"
    }
  },
  "required": [
    "goalId"
  ]
}

goal-attach-assumption-evidence

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).

Parameters2

assumptionId	string	required	UUID допущения
text	string	required	Текст evidence — наблюдение/данные, подтверждающие или опровергающие допущение

Raw schema

{
  "type": "object",
  "properties": {
    "assumptionId": {
      "type": "string",
      "description": "UUID допущения"
    },
    "text": {
      "type": "string",
      "description": "Текст evidence — наблюдение/данные, подтверждающие или опровергающие допущение"
    }
  },
  "required": [
    "assumptionId",
    "text"
  ]
}

goal-request-ac-change

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.

Parameters4

criterionId	string	required	UUID of the acceptance criterion to escalate
reason	string	required	Structured justification. For unreachable: what is unreachable and what was attempted. For wrong_criterion: which wording/threshold the owner never approved, or what finding showed the criterion measures something else
grounds	string	optional	Subject of the request: 'unreachable' (default) or 'wrong_criterion'
quotedFragment	string	optional	Verbatim slice of the criterion text claimed to be wrong — required when grounds=wrong_criterion, ignored otherwise

Raw schema

{
  "type": "object",
  "properties": {
    "criterionId": {
      "type": "string",
      "description": "UUID of the acceptance criterion to escalate"
    },
    "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",
      "description": "Subject of the request: 'unreachable' (default) or 'wrong_criterion'",
      "default": "unreachable"
    },
    "quotedFragment": {
      "type": "string",
      "description": "Verbatim slice of the criterion text claimed to be\nwrong — required when grounds=wrong_criterion,\nignored otherwise",
      "default": null
    }
  },
  "required": [
    "criterionId",
    "reason"
  ]
}

goal-resolve-escalation

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.

Parameters6

escalationId	string	required	UUID of the escalation to resolve
resolution	string	required	One of: edit, split, drop, reject
newText	string	optional	New AC text (required when resolution=edit)
note	string	optional	Optional comment explaining the decision
linkedGoalId	string	optional	Optional UUID of an existing goal to record as an audit reference (only meaningful when resolution=drop)
overrideResolvedBy	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "escalationId": {
      "type": "string",
      "description": "UUID of the escalation to resolve"
    },
    "resolution": {
      "type": "string",
      "description": "One of: edit, split, drop, reject"
    },
    "newText": {
      "type": "string",
      "description": "New AC text (required when resolution=edit)",
      "default": null
    },
    "note": {
      "type": "string",
      "description": "Optional comment explaining the decision",
      "default": null
    },
    "linkedGoalId": {
      "type": "string",
      "description": "Optional UUID of an existing goal to record as an\naudit reference (only meaningful when resolution=drop)",
      "default": null
    },
    "overrideResolvedBy": {
      "type": "string",
      "default": null
    }
  },
  "required": [
    "escalationId",
    "resolution"
  ]
}

goal-attach-file

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.

Parameters7

goalId	string	required	UUID of the goal the file illustrates
filename	string	required	Original file name (basename only; used for download + markdown alt)
contentBase64	string	required	File bytes, standard base64 (RFC 4648). Tiny files only — see description.
mimeType	string	optional	Optional MIME hint; server sniffs bytes when omitted or not whitelisted
caption	string	optional	Optional alt-text / caption used in the markdown fragment
createdBy	string	optional	Identifier of the uploading agent
contentSha256	string	optional	Optional hex sha256 of the raw bytes — server fails fast on transport corruption

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID of the goal the file illustrates"
    },
    "filename": {
      "type": "string",
      "description": "Original file name (basename only; used for download + markdown alt)"
    },
    "contentBase64": {
      "type": "string",
      "description": "File bytes, standard base64 (RFC 4648). Tiny files only — see description."
    },
    "mimeType": {
      "type": "string",
      "description": "Optional MIME hint; server sniffs bytes when omitted or not whitelisted",
      "default": null
    },
    "caption": {
      "type": "string",
      "description": "Optional alt-text / caption used in the markdown fragment",
      "default": null
    },
    "createdBy": {
      "type": "string",
      "description": "Identifier of the uploading agent",
      "default": null
    },
    "contentSha256": {
      "type": "string",
      "description": "Optional hex sha256 of the raw bytes — server fails fast on transport corruption",
      "default": null
    }
  },
  "required": [
    "goalId",
    "filename",
    "contentBase64"
  ]
}

goal-dismiss-red-team

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.

Parameters2

goalId	string	required	UUID цели
reason	string	required	Почему контрпример неприменим — от 80 символов, попадёт в историю цели

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "UUID цели"
    },
    "reason": {
      "type": "string",
      "description": "Почему контрпример неприменим — от 80 символов, попадёт в историю цели"
    }
  },
  "required": [
    "goalId",
    "reason"
  ]
}

goal-read-evidence-content

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.

Parameters6

evidenceId	string	required	UUID of file-backed evidence from goal-get
offset	integer	optional	Zero-based line offset
limit	integer	optional	Number of whole lines to return (1–500)
byteOffset	integer	optional	Zero-based byte offset for binary evidence
byteLimit	integer	optional	Number of bytes to return for binary evidence; omit with byteOffset for the complete original
binaryDelivery	string	optional	Complete binary: link to the original (default), or base64 fallback for clients without external links

Raw schema

{
  "type": "object",
  "properties": {
    "evidenceId": {
      "type": "string",
      "description": "UUID of file-backed evidence from goal-get"
    },
    "offset": {
      "type": "integer",
      "description": "Zero-based line offset",
      "default": 0
    },
    "limit": {
      "type": "integer",
      "description": "Number of whole lines to return (1–500)",
      "default": 100
    },
    "byteOffset": {
      "type": "integer",
      "description": "Zero-based byte offset for binary evidence",
      "default": null
    },
    "byteLimit": {
      "type": "integer",
      "description": "Number of bytes to return for binary evidence; omit with byteOffset for the complete original",
      "default": null
    },
    "binaryDelivery": {
      "type": "string",
      "description": "Complete binary: link to the original (default), or base64 fallback for clients without external links",
      "default": "link",
      "enum": [
        "link",
        "base64"
      ]
    }
  },
  "required": [
    "evidenceId"
  ]
}

goal-recent-unresolved

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).

Parameters4

project	string	required	Slug проекта
withinDays	integer	optional	Окно свежести (createdAt), default 14
statuses	array	optional	Подмножество {backlog,checking_ac,checking_ac_failed,checking_ac_errored,ready_for_work,in_progress,blocked}, default ["backlog"]
limit	integer	optional	Сколько записей вернуть, default 10

Raw schema

{
  "type": "object",
  "properties": {
    "project": {
      "type": "string",
      "description": "Slug проекта"
    },
    "withinDays": {
      "type": "integer",
      "description": "Окно свежести (createdAt), default 14",
      "default": null
    },
    "statuses": {
      "type": "array",
      "description": "Подмножество {backlog,checking_ac,checking_ac_failed,checking_ac_errored,ready_for_work,in_progress,blocked}, default [\"backlog\"]",
      "default": null,
      "items": {
        "type": "string"
      }
    },
    "limit": {
      "type": "integer",
      "description": "Сколько записей вернуть, default 10",
      "default": null
    }
  },
  "required": [
    "project"
  ]
}

goal-record-iteration-certificate

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.

Parameters12

goalId	string	required	Goal UUID
reworkClass	string	required	implementation, contract, proof_only, or unknown
afterFingerprint	string	required	Lowercase SHA-256 of the completed result
precondition	string	required	Observable state before the iteration
action	string	required	Action that changed the result
outcome	string	required	Observable completed result
acVerdict	string	required	matches, weak, mismatch, or errored
artifactRefs	array	required	Existing goal-owned evidence/goal_attachment refs
addressesFindingIds	array	optional	Registered finding UUIDs addressed by this iteration
repeatCheckEvidenceId	string	optional	Separate judged evidence UUID; mandatory when findings are addressed
beforeFingerprint	string	optional	Optional lowercase SHA-256 of the prior result
coverageDelta	array	optional	Structured coverage change

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "Goal UUID"
    },
    "reworkClass": {
      "type": "string",
      "description": "implementation, contract, proof_only, or unknown"
    },
    "afterFingerprint": {
      "type": "string",
      "description": "Lowercase SHA-256 of the completed result"
    },
    "precondition": {
      "type": "string",
      "description": "Observable state before the iteration"
    },
    "action": {
      "type": "string",
      "description": "Action that changed the result"
    },
    "outcome": {
      "type": "string",
      "description": "Observable completed result"
    },
    "acVerdict": {
      "type": "string",
      "description": "matches, weak, mismatch, or errored"
    },
    "artifactRefs": {
      "type": "array",
      "description": "Existing goal-owned evidence/goal_attachment refs",
      "items": {}
    },
    "addressesFindingIds": {
      "type": "array",
      "description": "Registered finding UUIDs addressed by this iteration",
      "default": [],
      "items": {
        "type": "string"
      }
    },
    "repeatCheckEvidenceId": {
      "type": "string",
      "description": "Separate judged evidence UUID; mandatory when findings are addressed",
      "default": null
    },
    "beforeFingerprint": {
      "type": "string",
      "description": "Optional lowercase SHA-256 of the prior result",
      "default": null
    },
    "coverageDelta": {
      "type": "array",
      "description": "Structured coverage change",
      "default": [],
      "items": {}
    }
  },
  "required": [
    "goalId",
    "reworkClass",
    "afterFingerprint",
    "precondition",
    "action",
    "outcome",
    "acVerdict",
    "artifactRefs"
  ]
}

goal-register-iteration-finding

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.

Parameters5

goalId	string	required	Goal UUID
kind	string	required	evidence_mismatch, red_team_hole, assumption_invalidated, acceptance_gap, or manual_checkpoint
summary	string	required	Concise observable weakness or gap
subjectRefs	array	required	Goal-scoped subject refs
sourceRefs	array	optional	Optional immutable source refs (validated structurally; resolved by the certificate recorder)

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string",
      "description": "Goal UUID"
    },
    "kind": {
      "type": "string",
      "description": "evidence_mismatch, red_team_hole, assumption_invalidated, acceptance_gap, or manual_checkpoint"
    },
    "summary": {
      "type": "string",
      "description": "Concise observable weakness or gap"
    },
    "subjectRefs": {
      "type": "array",
      "description": "Goal-scoped subject refs",
      "items": {}
    },
    "sourceRefs": {
      "type": "array",
      "description": "Optional immutable source refs (validated structurally; resolved by the certificate recorder)",
      "default": [],
      "items": {}
    }
  },
  "required": [
    "goalId",
    "kind",
    "summary",
    "subjectRefs"
  ]
}

goal-start-iteration-tracking

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.

Parameters1

goalId

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "goalId": {
      "type": "string"
    }
  },
  "required": [
    "goalId"
  ]
}

account-delete

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.

Parameters5

confirm_passphrase	string	optional	Фраза из вызова 1 (для вызова 2)
objects_total	integer	optional	projects + goals из инвентаря (для вызова 2)
reasoning_answer	string	optional	Ответ на reasoning-риддл из вызова 1
acknowledge	string	optional	Точная фраза подтверждения
reason	string	optional	Зачем удаляешь (свободный текст, ≥10 символов)

Raw schema

{
  "type": "object",
  "properties": {
    "confirm_passphrase": {
      "type": "string",
      "description": "Фраза из вызова 1 (для вызова 2)",
      "default": null
    },
    "objects_total": {
      "type": "integer",
      "description": "projects + goals из инвентаря (для вызова 2)",
      "default": null
    },
    "reasoning_answer": {
      "type": "string",
      "description": "Ответ на reasoning-риддл из вызова 1",
      "default": null
    },
    "acknowledge": {
      "type": "string",
      "description": "Точная фраза подтверждения",
      "default": null
    },
    "reason": {
      "type": "string",
      "description": "Зачем удаляешь (свободный текст, ≥10 символов)",
      "default": null
    }
  }
}

README.md4 KBView on GitHub

Planner MCP (proof-of-done)

Evidence-gated task verification for AI agents. Hosted MCP server — nothing to install.

Search aliases such as MCP Planner, Planner MCP, install mcp planner, and установи mcp planner refer to this official server: com.monopoly-gold.planner/mcp.

MCP endpoint: https://planner.monopoly-gold.com/_mcp

What it does

Planner prevents AI agents from marking tasks "done" on trust alone. Every goal goes through a verification gate:

Decompose — break a goal into acceptance criteria with behavioral checks
Attach evidence — screenshot, curl output, file, or text artifact per criterion
Independent judge — LLM evaluates evidence against the criterion and accepts or rejects

Goals stay open until every acceptance criterion has passing evidence.

Key features

Goal hierarchy — projects, milestones, goals, tasks with parent-child relationships
Acceptance criteria — behavioral, observable checks (not "Denis approves")
Evidence model — attach files or text per criterion; plain notes don't satisfy the gate
LLM judge — independent verdict on each piece of evidence
Gate-keeper interview — 3 questions on goal creation: why, where in the tree, how we'll verify
Dependencies & blockers — cross-goal blocking with auto-unblock on resolution
Tree & summary views — full hierarchy traversal and project-level summaries

MCP tools (24)

Category	Tools
Projects	`project-list`, `project-get`, `project-create`, `project-delete`, `project-add-dependency`, `project-remove-dependency`
Goals	`goal-list`, `goal-get`, `goal-tree`, `goal-create`, `goal-update`, `goal-delete`, `goal-move`, `goal-reorder`, `goal-summary`, `goal-todo`
Criteria	`goal-add-criterion`
Evidence	`goal-attach-evidence`, `goal-add-evidence-text`, `goal-remove-evidence`, `goal-request-upload`
Blockers	`goal-block`, `goal-remove-blocker`
Account	`account-delete`

Connect

Planner is a hosted remote MCP server using streamable HTTP transport with OAuth 2.1 authentication and Dynamic Client Registration (RFC 7591).

Codex — “установи mcp planner”

Run these commands in Codex CLI:

bash

codex mcp add planner --url https://planner.monopoly-gold.com/_mcp
codex mcp login planner
codex mcp list

Planner signs the user in through browser OAuth. There is no Planner token to create or paste, and no package or repository to clone. After login, ask Codex to list your Planner projects; a successful project-list tool call confirms that the connection is live (an empty list is valid for a new account).

Canonical guide: https://planner.monopoly-gold.com/connect/codex

Claude Desktop / Claude Code

Add to your MCP configuration:

json

{
  "mcpServers": {
    "planner": {
      "type": "url",
      "url": "https://planner.monopoly-gold.com/_mcp"
    }
  }
}

OAuth login happens automatically on first connection.

Any MCP client

Point your client to https://planner.monopoly-gold.com/_mcp — the server supports MCP discovery and standard OAuth 2.1 flow.

Directory listings

Directory	Status	Link
Glama	✅ Live, Healthy	glama.ai/mcp/connectors/…/planner-proof-of-done
mcp.so	✅ Published	mcp.so/server/planner
awesome-mcp-servers	⏳ PR under review	PR #8708

License

Proprietary. Planner is a hosted service — this repository contains documentation only.

Install

Tools (43)

project-listproject-createproject-getproject-updateproject-deleteproject-add-dependencyproject-remove-dependencygoal-list

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://planner.monopoly-gold.com/_mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://planner.monopoly-gold.com/_mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

com.monopoly-gold.planner/mcp (MCP) — Planner

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

project-list

project-create

project-get

project-update

project-delete

project-add-dependency

project-remove-dependency

goal-list

goal-create

goal-get

goal-update

goal-delete

goal-move

goal-reorder

goal-block

goal-remove-blocker

goal-todo

goal-add-note

goal-remove-note

goal-tree

goal-summary

goal-add-criterion

goal-update-criterion

goal-remove-criterion

goal-attach-evidence

goal-request-upload

goal-add-evidence-text

goal-remove-evidence

goal-add-assumption

goal-update-assumption

goal-remove-assumption

goal-suggest-assumptions

goal-attach-assumption-evidence

goal-request-ac-change

goal-resolve-escalation

goal-attach-file

goal-dismiss-red-team

goal-read-evidence-content

goal-recent-unresolved

goal-record-iteration-certificate

goal-register-iteration-finding

goal-start-iteration-tracking

account-delete

Planner MCP (proof-of-done)

What it does

Key features

MCP tools (24)

Connect

Codex — “установи mcp planner”

Claude Desktop / Claude Code

Any MCP client

Directory listings

Links

License

Install

Remote endpoint

Related servers