GodPrompt MCP Server
GodPrompt MCP + Agent Skill for coding agents with TDD, debugging, verification, and task routing.
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": {
"god-prompt-mcp": {
"command": "npx",
"args": [
"god-prompt-mcp"
]
}
}
}実行可能なパッケージ
1.0.33stdioリモートエンドポイント
https://god-prompt-mcp.tomi-seregi99.workers.dev/mcpstreamable-httpできること
ツール一覧
ツール（7）
🟢get_god_prompt
Returns the complete GodPrompt.md — a single-file universal system prompt for AI software development (47KB, ~1145 lines). Use this when you want the full payload in one shot. For progressive disclosure (smaller context), use get_core_skill and the reference tools instead.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢get_core_skill
Returns SKILL.md — the lean core protocol (~16KB) covering the universal 6-phase protocol, Three Iron Laws, and task auto-classification. Load it at the start of a task or after a context reset, then reuse that context instead of reloading it on every message. Start here for progressive disclosure.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢get_protocols
Returns references/01-PROTOCOLS.md — deep execution guides for each task type (BUILD, DEBUG, REFACTOR, CONTENT, DESIGN, SHIP, ANALYZE, AUTOMATE, PLAN). Load this when the task requires detailed protocol steps beyond the core skill. ~13KB.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢get_gates
Returns references/02-GATES.md — verification checklists, THE GATE (pre-completion verification), and structured report templates for every deliverable type. Load when you need to verify work before claiming completion. ~9KB.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢get_anti_patterns
Returns references/03-ANTI-PATTERNS.md — red flags, rationalizations, and recovery patterns. Covers the 10 most dangerous anti-patterns that lead to broken code, scope creep, and false confidence. Load when you catch yourself rationalizing. ~9KB.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢classify_task(description)
Classify one concrete software-development task into one of GodPrompt's 9 task types (BUILD, DEBUG, REFACTOR, CONTENT, DESIGN, SHIP, ANALYZE, AUTOMATE, PLAN), or UNCLASSIFIED when no reliable route is detected. Returns JSON with task_type, deterministic confidence, protocol, matched_signals, alternative_task_types, ambiguous, and recommendation; use it for routing before loading detailed workflow text.
入力スキーマ
{
"type": "object",
"properties": {
"description": {
"type": "string",
"minLength": 3,
"maxLength": 1000,
"pattern": "[\\p{L}\\p{N}]",
"description": "The task description to classify, e.g. 'fix the login bug' or 'build a REST API for user auth'"
}
},
"required": [
"description"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_version
Returns JSON with the GodPrompt content version, MCP server version, repository, bundled file sizes and purposes, and task-type/protocol catalog. Use it to verify which GodPrompt content/server version a client is connected to; use the content retrieval tools when you need the actual workflow text.
入力スキーマ
{
"type": "object",
"properties": {}
}コミュニティ
エビデンス