School Timetable Builder
Build a full weekly timetable for a primary school (classes, teachers, rooms) via chat.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
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": {
"timetable-builder": {
"url": "https://timetable-builder.wilbek.workers.dev/mcp"
}
}
}远程端点
https://timetable-builder.wilbek.workers.dev/mcpstreamable-http它能做什么
工具清单
工具（5）
🟢get_interview_guide
Returns the interview guide: which questions to ask the user, default values, engine limits and the exact format of the 8 input files. Call this first.
输入模式
{
"type": "object",
"properties": {}
}🟢validate_input(files, user_language, user_country)
Checks the 8 input files in a few seconds without creating a timetable: file structure, engine limits and a capacity analysis (enough teachers/time?). Returns VALID (with warnings) or INVALID (with reasons). Always run this before create_schedule.
输入模式
{
"type": "object",
"properties": {
"files": {
"type": "object",
"properties": {
"skolekonfig": {
"type": "string",
"description": "Content of the 'skolekonfig' file as text (JSON or CSV, see the interview guide)"
},
"laerere": {
"type": "string",
"description": "Content of the 'laerere' file as text (JSON or CSV, see the interview guide)"
},
"plan": {
"type": "string",
"description": "Content of the 'plan' file as text (JSON or CSV, see the interview guide)"
},
"min_dag": {
"type": "string",
"description": "Content of the 'min_dag' file as text (JSON or CSV, see the interview guide)"
},
"bindings": {
"type": "string",
"description": "Content of the 'bindings' file as text (JSON or CSV, see the interview guide)"
},
"dagsstruktur": {
"type": "string",
"description": "Content of the 'dagsstruktur' file as text (JSON or CSV, see the interview guide)"
},
"lokaler": {
"type": "string",
"description": "Content of the 'lokaler' file as text (JSON or CSV, see the interview guide)"
},
"minmax": {
"type": "string",
"description": "Content of the 'minmax' file as text (JSON or CSV, see the interview guide)"
}
},
"required": [
"skolekonfig",
"laerere",
"plan",
"min_dag",
"bindings",
"dagsstruktur",
"lokaler",
"minmax"
],
"description": "The 8 input files, exactly as described in the interview guide's 'submission' and 'topics'. JSON files are sent as JSON text inside the string; empty CSV files contain only the header line."
},
"user_language": {
"description": "Optional, for anonymous usage statistics: the language you talk to the user in (e.g. 'da', 'en'). Fill it in if you know it; never ask the user.",
"type": "string",
"maxLength": 20
},
"user_country": {
"description": "Optional, for anonymous usage statistics: the school's country (e.g. 'Denmark') if the user has mentioned it. Never ask the user just for this.",
"type": "string",
"maxLength": 60
}
},
"required": [
"files"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡create_schedule(files, user_language, user_country)
Starts calculating the full timetable from the 8 input files (validate them first). Returns a job_id at once; the calculation takes about 5-8 minutes. Then keep calling get_schedule_result with the job_id in the same reply until it is done.
输入模式
{
"type": "object",
"properties": {
"files": {
"type": "object",
"properties": {
"skolekonfig": {
"type": "string",
"description": "Content of the 'skolekonfig' file as text (JSON or CSV, see the interview guide)"
},
"laerere": {
"type": "string",
"description": "Content of the 'laerere' file as text (JSON or CSV, see the interview guide)"
},
"plan": {
"type": "string",
"description": "Content of the 'plan' file as text (JSON or CSV, see the interview guide)"
},
"min_dag": {
"type": "string",
"description": "Content of the 'min_dag' file as text (JSON or CSV, see the interview guide)"
},
"bindings": {
"type": "string",
"description": "Content of the 'bindings' file as text (JSON or CSV, see the interview guide)"
},
"dagsstruktur": {
"type": "string",
"description": "Content of the 'dagsstruktur' file as text (JSON or CSV, see the interview guide)"
},
"lokaler": {
"type": "string",
"description": "Content of the 'lokaler' file as text (JSON or CSV, see the interview guide)"
},
"minmax": {
"type": "string",
"description": "Content of the 'minmax' file as text (JSON or CSV, see the interview guide)"
}
},
"required": [
"skolekonfig",
"laerere",
"plan",
"min_dag",
"bindings",
"dagsstruktur",
"lokaler",
"minmax"
],
"description": "The 8 input files, exactly as described in the interview guide's 'submission' and 'topics'. JSON files are sent as JSON text inside the string; empty CSV files contain only the header line."
},
"user_language": {
"description": "Optional, for anonymous usage statistics: the language you talk to the user in (e.g. 'da', 'en'). Fill it in if you know it; never ask the user.",
"type": "string",
"maxLength": 20
},
"user_country": {
"description": "Optional, for anonymous usage statistics: the school's country (e.g. 'Denmark') if the user has mentioned it. Never ask the user just for this.",
"type": "string",
"maxLength": 60
}
},
"required": [
"files"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_schedule_result(job_id, view, names)
Gets the status or result of a job from create_schedule (or a slow validate_input). While running: progress. When done: a compact timetable as text plus a link (valid 1 hour) to the full JSON result. view='classes' (default) = one table per class, 'teachers' = one per teacher incl. preparation time, 'summary' = key figures and lists of classes/teachers only. Use 'names' to get only some classes/teachers (recommended for big schools). If impossible: the reasons.
输入模式
{
"type": "object",
"properties": {
"job_id": {
"type": "string",
"description": "job_id from create_schedule or validate_input"
},
"view": {
"description": "What to show when done (default 'classes')",
"type": "string",
"enum": [
"classes",
"teachers",
"summary"
]
},
"names": {
"description": "Only these classes (e.g. '1.A') or teacher codes (e.g. 'T01')",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"job_id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡send_feedback(message, sentiment, job_id, user_language, user_country)
Passes the user's feedback about the timetable service on to its developer (what worked, what did not, wishes). Only call it when the user has said they want to give feedback, and send what the user said in their own words (you may shorten it; any language is fine). Never include teacher names, other personal data or the school's data files. Tell the user briefly that it was sent. Nobody replies through this channel - if the user wants an answer, give them the support email [email protected].
输入模式
{
"type": "object",
"properties": {
"message": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "The user's feedback, without names or other personal data"
},
"sentiment": {
"description": "Overall tone of the feedback, if clear",
"type": "string",
"enum": [
"positive",
"negative",
"mixed"
]
},
"job_id": {
"description": "job_id of the timetable the feedback is about, if any",
"type": "string",
"maxLength": 40
},
"user_language": {
"description": "Optional, for anonymous usage statistics: the language you talk to the user in (e.g. 'da', 'en'). Fill it in if you know it; never ask the user.",
"type": "string",
"maxLength": 20
},
"user_country": {
"description": "Optional, for anonymous usage statistics: the school's country (e.g. 'Denmark') if the user has mentioned it. Never ask the user just for this.",
"type": "string",
"maxLength": 60
}
},
"required": [
"message"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}社区
证据