specpack
Audit and write CLAUDE.md / AGENTS.md / Cursor rules; generate full build specs for new projects.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"specpack": {
"command": "npx",
"args": [
"specpack"
]
}
}
}実行可能なパッケージ
0.1.0stdioリモートエンドポイント
https://prompt-generator-website.com/mcpstreamable-httpできること
ツール一覧
ツール（5）
🟢list_project_types
The project types the spec generator knows (saas, ecommerce, business, marketplace, blog, webapp, landing), with what each covers.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_questionnaire(type)
The questions for one project type: universal questions first, then type-specific ones. Each has an id, a type (text, textarea, select, radio, multiselect, boolean, number), options where relevant, and sometimes a condition (ask it only when another answer matches). Answer from what you know of the project, then pass the answers to generate_spec. Only project_name and project_description are required; skipped questions fall back to defaults.
入力スキーマ
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"saas",
"ecommerce",
"business",
"marketplace",
"blog",
"webapp",
"landing"
],
"description": "Project type id"
}
},
"required": [
"type"
],
"additionalProperties": false
}🟡generate_spec(type, answers, files)
Turns questionnaire answers into a complete build specification (stack, database schema, auth flows, pages, design system, SEO, security, legal, deployment, file structure) and the matching agent files. Deterministic: the same answers always give the same bytes. Values: select/radio = one option value, multiselect = array of option values, boolean = true/false, number = number. Returns the requested files; by default AGENTS.md (full spec + working agreement) and CLAUDE.md (imports AGENTS.md) — write them at the repository root. Uses one spec from the quota (2 free without an API key).
入力スキーマ
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"saas",
"ecommerce",
"business",
"marketplace",
"blog",
"webapp",
"landing"
]
},
"answers": {
"type": "object",
"description": "Question id => value, as described by get_questionnaire",
"additionalProperties": true
},
"files": {
"type": "array",
"items": {
"type": "string",
"enum": [
"spec.md",
"AGENTS.md",
"CLAUDE.md",
".cursor/rules/project.mdc",
".cursorrules",
".windsurfrules",
".github/copilot-instructions.md",
"README.md"
]
},
"description": "Files to return. Default: [\"AGENTS.md\", \"CLAUDE.md\"]"
}
},
"required": [
"type",
"answers"
],
"additionalProperties": false
}🟢draft_answers(description, type)
Asks the server's AI (Claude) to fill the whole questionnaire from a plain-language project description; returns the project type, the answers and the assumptions it made. Takes 10-40 s and consumes one AI draft (3 free without an API key). Prefer answering get_questionnaire yourself when you already know the project; use this when you only have a one-line idea. Review the assumptions with the user before calling generate_spec.
入力スキーマ
{
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "What the project is, for whom, and what it must do (10-4000 characters)"
},
"type": {
"type": "string",
"enum": [
"saas",
"ecommerce",
"business",
"marketplace",
"blog",
"webapp",
"landing"
],
"description": "Optional: force the project type"
}
},
"required": [
"description"
],
"additionalProperties": false
}🟢get_usage
Current plan and quota usage (specs and AI drafts) for the API key, or for this address when no key is set.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}コミュニティ
エビデンス