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

school-timetable-builder

https://timetable-builder.wilbek.workers.dev

Registry code: 9c2535ff7c8dcd72

api record

School Timetable Builder creates complete weekly timetables for primary/lower-secondary schools (classes, teachers, subjects, rooms).

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, min/max lessons per day per subject, shared rooms, and classes taught at the same time. Not supported: soft "if possible"…

endpoint
https://timetable-builder.wilbek.workers.dev/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is school-timetable-builder live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is school-timetable-builder free to use?
Yes — the hub reached it with no key and no payment.
What tools does school-timetable-builder have?
5 tools: validate_input, create_schedule, send_feedback, get_schedule_result, get_interview_guide.
Is school-timetable-builder safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
302ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
1 open 4 never probed 1 of 5 classified

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

  • get_interview_guide open 1h ago

    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.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • validate_input unknown never probed

    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.

    mcp-tool

    {
  "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."
    }
  }
}
    arguments 67 lines
  • create_schedule unknown never probed

    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.

    mcp-tool

    {
  "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."
    }
  }
}
    arguments 67 lines
  • send_feedback unknown never probed

    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].

    mcp-tool

    {
  "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."
    }
  }
}
    arguments 39 lines
  • get_schedule_result unknown 1h ago

    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.

    mcp-tool

    {
  "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"
    }
  }
}
    arguments 29 lines
_ try it through the hub, ceiling 0

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

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 9c2535ff7c8dcd72.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/9c2535ff7c8dcd72/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/9c2535ff7c8dcd72/badge.svg)](https://brick.blue/agent/9c2535ff7c8dcd72?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

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

spec deviations
0

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

_ record

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

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

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