planner

Compute real duty rosters from your AI assistant - rule-based vigotime planner, API key or OAuth.

我该使用它吗

质量与安全性

B
描述质量
90%
模式完整度
62%
命名质量
80%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(2)

  • LOWTool 'solve_result' description lacks action verb在 solve_result 中
  • LOWTool 'account_balance' description lacks action verb在 account_balance 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~733token 数(工具定义)
~577 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.57%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "planner": {
      "url": "https://api.vigotime.com/mcp"
    }
  }
}

远程端点

https://api.vigotime.com/mcpstreamable-http

它能做什么

工具清单

工具(6)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟡solve_submit(payload)

Reicht einen Dienstplan-Solve-Job ein. `payload` ist der self-contained Request: Pflicht: start_date, end_date (ISO), department {id}, employees [{id, contractHoursPerWeek, qualificationIds}], shifts [{id, departmentId, name, startTime, endTime, shiftType, minStaff}]. Optional u. a.: planning_rules, wishes, vacations, sick_leaves, holiday_dates, locked_assignments, social_points, wish_costs, config {timeout_seconds}. vacations darf Termine NACH end_date enthalten — noetig bei Datums-Kopplungsregeln mit Block-Tagen hinter dem Fenster (siehe Instructions). Datenschutz: IDs statt Namen verwenden. Antwort: {job_id, status}.

输入模式

{
  "type": "object",
  "properties": {
    "payload": {
      "additionalProperties": true,
      "title": "Payload",
      "type": "object"
    }
  },
  "required": [
    "payload"
  ],
  "title": "solve_submitArguments"
}

输出模式

{
  "type": "object",
  "additionalProperties": true,
  "title": "solve_submitDictOutput"
}
⚪solve_status(job_id)

Status eines Solve-Jobs (pending/running/completed/failed) inkl. Fortschritt.

输入模式

{
  "type": "object",
  "properties": {
    "job_id": {
      "title": "Job Id",
      "type": "string"
    }
  },
  "required": [
    "job_id"
  ],
  "title": "solve_statusArguments"
}

输出模式

{
  "type": "object",
  "additionalProperties": true,
  "title": "solve_statusDictOutput"
}
⚪solve_result(job_id)

Ergebnis eines fertigen Solve-Jobs: assignments [{employee_id, shift_id, date}], unassigned_shifts mit Begründung, Statistiken.

输入模式

{
  "type": "object",
  "properties": {
    "job_id": {
      "title": "Job Id",
      "type": "string"
    }
  },
  "required": [
    "job_id"
  ],
  "title": "solve_resultArguments"
}

输出模式

{
  "type": "object",
  "additionalProperties": true,
  "title": "solve_resultDictOutput"
}
⚪account_balance

Aktuelles Token-Guthaben der eigenen Organisation (Solves kosten Tokens).

输入模式

{
  "type": "object",
  "properties": {},
  "title": "account_balanceArguments"
}

输出模式

{
  "type": "object",
  "additionalProperties": true,
  "title": "account_balanceDictOutput"
}
⚪service_info

Build-Stand des laufenden Planner-Service: version (fortlaufende Build-Nummer), gitCommit, buildTime (UTC). Fuer Support-Anfragen und um Ergebnisse einem Software-Stand zuzuordnen.

输入模式

{
  "type": "object",
  "properties": {},
  "title": "service_infoArguments"
}

输出模式

{
  "type": "object",
  "additionalProperties": true,
  "title": "service_infoDictOutput"
}
⚪example_payload(kind)

Ein sofort lauffähiger Beispiel-Payload für solve_submit. kind='simple' (1 Woche, 3 MA, 2 Schichten), kind='wishes' (Wünsche, Social Points, Wunschkosten) oder kind='rules' (ArbZG-Planungsregeln: 11 h Ruhe hart + max. 5 Folgetage — zeigt, wie Regeln den Plan formen; Param-Namen sind exakt, falsche werden still ignoriert).

输入模式

{
  "type": "object",
  "properties": {
    "kind": {
      "default": "simple",
      "title": "Kind",
      "type": "string"
    }
  },
  "title": "example_payloadArguments"
}

输出模式

{
  "type": "object",
  "additionalProperties": true,
  "title": "example_payloadDictOutput"
}

社区

评价此服务器

证据

最近观测

已验证未记录版本6 个工具
已验证未记录版本6 个工具