E
ESQ Builder
Local@mo9652962-aiScience & Education
About ESQ Builder
ESQ 1.0 question bank package toolchain (Mori quiz machine): build(auto_fix) → validate (dual-track validation) → upload/publish + kajweb vocabulary parsing and hot word statistics
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
5Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| papers | array | Yes | [{paperKey, year, units:[{unitKey, type(cloze|reading|part_b), title, sequence, passage?, candidates?, questions:[...]}]}] - cloze: passage.blocks[].text は {{blank:N}} の二重中括弧で空欄を示します(単一中括弧ではありません!);語彙バンク問題では unit.candidates=[{key:"A",content:"..."}] を使用し、questions に options は記述しません - reading: questions に options=[{key:"A",content:"..."}] を記述します - question: {questionKey, number, type:"single_choice", stem, score} |
| answers | object | Yes | {paperKey: {questionKey: {correctOption:"B", score: 2}}} —— Required for every blank; correctOption must exist among the options for that question. |
| auto_fix | boolean | No | When true, first automatically fixes mechanical issues, then builds—including rebuilding externalKey values containing Chinese in the cn.xxx.y2021.u1 style (and renaming answers keys accordingly), converting single-brace {blank:N} to double braces, and filling in missing sequence values with defaults. Repair details are in the returned fixes array; judgment-based issues (blank count ≠ question count, answer not among options) still produce errors. Defaults to false (reject + actionable errors). |
| manifest | object | Yes | {packageId, contentVersion, title, subject, publisher, license:{notice}, source:{description}} |
| output_path | string | Yes | Absolute path to the output ZIP |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
Markdown supported
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.