School Timetable Builder is an MCP server published by io.github.wilbek-source, hosted at timetable-builder.wilbek.workers.dev. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 5 tools, including get_interview_guide, validate_input, create_schedule, get_schedule_result, send_feedback.
Build a full weekly timetable for a primary school (classes, teachers, rooms) via chat.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
No parameters.
{
"name": "get_interview_guide",
"title": "Get interview guide",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}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.
None yet. Changes appear after a server's second daily check.
| Parameter | Type | Description |
|---|---|---|
| files * | object | 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_country | string | 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. |
| user_language | string | 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. |
{
"name": "validate_input",
"title": "Validate input files (free)",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"files"
],
"properties": {
"files": {
"type": "object",
"required": [
"skolekonfig",
"laerere",
"plan",
"min_dag",
"bindings",
"dagsstruktur",
"lokaler",
"minmax"
],
"properties": {
"plan": {
"type": "string",
"description": "Content of the 'plan' 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)"
},
"laerere": {
"type": "string",
"description": "Content of the 'laerere' 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)"
},
"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)"
},
"skolekonfig": {
"type": "string",
"description": "Content of the 'skolekonfig' 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)"
}
},
"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_country": {
"type": "string",
"maxLength": 60,
"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."
},
"user_language": {
"type": "string",
"maxLength": 20,
"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."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| files * | object | 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_country | string | 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. |
| user_language | string | 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. |
{
"name": "create_schedule",
"title": "Create timetable",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"files"
],
"properties": {
"files": {
"type": "object",
"required": [
"skolekonfig",
"laerere",
"plan",
"min_dag",
"bindings",
"dagsstruktur",
"lokaler",
"minmax"
],
"properties": {
"plan": {
"type": "string",
"description": "Content of the 'plan' 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)"
},
"laerere": {
"type": "string",
"description": "Content of the 'laerere' 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)"
},
"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)"
},
"skolekonfig": {
"type": "string",
"description": "Content of the 'skolekonfig' 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)"
}
},
"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_country": {
"type": "string",
"maxLength": 60,
"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."
},
"user_language": {
"type": "string",
"maxLength": 20,
"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."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| view | string | What to show when done (default 'classes') |
| names | array | Only these classes (e.g. '1.A') or teacher codes (e.g. 'T01') |
| job_id * | string | job_id from create_schedule or validate_input |
{
"name": "get_schedule_result",
"title": "Get timetable result",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"job_id"
],
"properties": {
"view": {
"enum": [
"classes",
"teachers",
"summary"
],
"type": "string",
"description": "What to show when done (default 'classes')"
},
"names": {
"type": "array",
"items": {
"type": "string"
},
"description": "Only these classes (e.g. '1.A') or teacher codes (e.g. 'T01')"
},
"job_id": {
"type": "string",
"description": "job_id from create_schedule or validate_input"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}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 timetablingengine.support@gmail.com.
| Parameter | Type | Description |
|---|---|---|
| job_id | string | job_id of the timetable the feedback is about, if any |
| message * | string | The user's feedback, without names or other personal data |
| sentiment | string | Overall tone of the feedback, if clear |
| user_country | string | 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. |
| user_language | string | 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. |
{
"name": "send_feedback",
"title": "Send feedback to the developer",
"description": "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 timetablingengine.support@gmail.com.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"message"
],
"properties": {
"job_id": {
"type": "string",
"maxLength": 40,
"description": "job_id of the timetable the feedback is about, if any"
},
"message": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "The user's feedback, without names or other personal data"
},
"sentiment": {
"enum": [
"positive",
"negative",
"mixed"
],
"type": "string",
"description": "Overall tone of the feedback, if clear"
},
"user_country": {
"type": "string",
"maxLength": 60,
"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."
},
"user_language": {
"type": "string",
"maxLength": 20,
"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."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}School Timetable Builder creates complete weekly timetables for primary/lower-secondary schools (classes, teachers, subjects, rooms), Monday-Friday or Monday-Saturday (Saturday may be shorter). All rules are firm rules: teacher availability (block any day or lesson, e.g. a teacher not available after lesson 4 on Fridays or at another school on Mondays), blocked lessons for a class or grade, teacher workload, planning time at school placed in the teacher's timetable with no empty gaps by default, fixed teachers, double lessons, max lessons per day per subject, shared rooms, classes taught at the same time, groups within a class taught at the same time (e.g. religion or language groups), and co-teaching (two teachers in the same lesson). Not supported: soft "if possible" preferences weighed against each other, whole-day events, student-choice course timetables. Workflow: 1. Call get_interview_guide FIRST and follow it: interview the user in their own language, one topic at a time, and build the 8 input files. 2. Let the user give real teacher names as usual, but before sending anything replace each name with a code (T01, T02, ...). Show the user the code list once and keep it in the conversation - you need it to translate the result back. 3. Call validate_input (free, seconds) and fix every problem with the user before going on. 4. Call create_schedule only after a successful validation and the user's go-ahead, asked for after the validation (a wish like "give me the finished timetable" in the first message is not a go-ahead). It takes about 5-8 minutes (longer if others are queued). 5. In the SAME reply, keep calling get_schedule_result with the job_id until it is done (each call waits up to ~25 seconds). Do not end your reply while it runs and never promise to tell the user later - you cannot send a message on your own, so the user would be left waiting. If the result is IMPOSSIBLE or an error: explain it to the user, suggest changes and let the user choose. Never change the school's rules or data yourself (fixed teachers, double lessons, daily limits, groups, lesson numbers ...) and never start a new create_schedule before the user has agreed to the change - each job counts against a daily limit. 6. The service does NOT store anything for the user: input files are deleted right after each job, results within 24 hours, and the full-result link expires after 1 hour. So as soon as the timetable is ready: fetch both views (classes and teachers), replace every teacher code with the real name, and give the user the finished timetable as files in this chat (e.g. a spreadsheet with one sheet per class and one per teacher, or a printable document), plus a 'School data' file with all data used so they can re-run later (see the guide). Those files are the user's only copy. Never say the timetable is saved in the service, can be fetched again later, or can be shared via a link from it. 7. After handing over the finished timetable, add ONE short line (once per conversation) that the user can tell you if they have feedback for the developer. If the user then gives feedback, pass it on with send_feedback. The service is free to use, with shared limits.
Names, descriptions and schemas were written by the server and are shown as data.