Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者による説明(英語の原文)
Resolve a developer profile to exactly one project blueprint and return its CI-tested setup recipe.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"forgeprint": {
"command": "npx",
"args": [
"-y",
"forgeprint-mcp"
]
}
}
}ターミナルでこれを実行します
claude mcp add forgeprint -- npx -y forgeprint-mcpプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"forgeprint": {
"command": "npx",
"args": [
"-y",
"forgeprint-mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"forgeprint": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"forgeprint-mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月6日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント forgeprint で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.4.5)がレジストリに届いたのは31 日前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.jsも必要です。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, Dechonet MCP
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Others say "here are 200 skills, go find yours." Forgeprint says "tell me who you are and what you're building — here is your package."
Forgeprint is a community-grown blueprint catalog and MCP server that lets a coding agent bootstrap a new project with the right context in one shot: the AGENTS.md, the skills, the MCP and plugin configuration, and a deterministic setup recipe the agent can execute.
Status: pre-release. A catalog of blueprints, experts, crews and
integrations, working tooling, and an MCP server with all ten tools, published
and connectable today. With Claude Code:
`bash
claude mcp add forgeprint -- npx -y forgeprint-mcp
`
On Windows PowerShell, quote the separator:
claude mcp add forgeprint "--" npx -y forgeprint-mcp.
Any MCP client can connect; the site
has the command or configuration for each of the nine registered agents, and
the catalog with its current counts. Roadmap has the rest.
Every new project starts cold. You hunt down the requirements, write the rule file by hand, wire up the MCP servers, pick the plugins, and get the setup steps wrong twice before they work. Hours of it — repeated by everyone, on every project, forever.
That knowledge is not hard to write down. It is just never written down in a form another agent can use.
You do not search Forgeprint. You describe yourself and your goal, and it returns exactly one blueprint.
You: I know C#. I want to build a multi-tenant SaaS API.
Agent: [resolve] → Forgeprint returns questions: which database, which auth, self-hosted or cloud? You: Postgres, JWT, cloud. Agent: [resolve] → one blueprint, why it was chosen, what is missing on this machine, and the setup plan.
When the profile is incomplete, the resolver does not guess: it returns the questions your agent should ask you. When two candidates are genuinely close, it returns both as a question and lets you pick — never as a list to sift through. When nothing fits, it says so, names the closest blueprint, explains why it does not fit, and offers to file a request. It never invents a match.
Scoring is weighted: a language you already know beats everything else.
setup.md is a script, not prose. Every step is numbered, is a single command or a single file operation, and ends with a verification command. Versions are pinned. Option branches are explicit. The agent executes it; Forgeprint itself installs nothing and runs nothing on your machine.
Every pull request passes schema validation, a setup test that actually runs the recipe in a clean container, and a duplicate report against the closest existing blueprint. Two blueprints may not claim the same stack, project type and requirements — a better one replaces the old one instead of sitting next to it.
There is no inheritance and there are no variants. Variation is expressed as options, capped at three fields with three values each, so the whole matrix stays testable. See ADR 0001.
Forgeprint follows the existing specs — AGENTS.md, SKILL.md, marketplace.json — so its output drops into the tools you already use, and skills remain installable through the usual channels:
npx skills add forgeprint/forgeprint # skills.sh CLI
gh skill install forgeprint/forgeprint blueprint-author
Both are verified against the real tools before each release, and forgeprint validate fails on a skill that would not install — see ADR 0006.
Forgeprint is not trying to replace most of these. It sits in the gap between them.
| Project | What it does | How Forgeprint differs |
|---|---|---|
microsoft/skills | 170+ Azure/Foundry skills, an AGENTS.md template, ready MCP configs | A catalog you browse; no matching, and Azure-shaped |
github/awesome-copilot | Community instructions, prompts and skills for Copilot | A rule collection; no setup recipe, no resolver |
github/spec-kit | Spec-driven development: spec → plan → tasks | A process tool. Forgeprint delivers the context package and the recipe — complementary, not competing |
agent-rules-mcp | An MCP that fetches rule files from any GitHub repo | Fetches files; no selection, no schema, no setup, no quality gate |
codeops-mcp | Universal coding rules, generates project.md from an existing project | The opposite direction: it analyses projects that exist. Forgeprint bootstraps ones that do not |
awesome-cursorrules | A Cursor .mdc rule collection | One tool, one file type; no setup, no MCP |
skills.sh, gh skills install | Skill distribution standard and CLI | Distribution infrastructure that Forgeprint builds on top of, not a competitor |
You point your agent at the MCP server and talk normally. docs/mcp.md has the connection details and a worked exchange.
| Tool | What you get |
|---|---|
resolve | Either the questions to ask you, or one blueprint with its rationale, missing tools and setup plan |
search_blueprints | Matching blueprints with scores, when you want to look yourself |
get_blueprint | The manifest and every file, with option branches already resolved |
compare_blueprints | A pros-and-cons table for 2–4 candidates, built from their overview.md files |
validate_blueprint | Schema errors and a similarity report, for contributors |
request_blueprint | A GitHub issue payload when nothing matches |
recommend_experts | For a task, at most one crew or at most three experts, each with a reason — never a list to browse |
get_expert | One expert: its SKILL.md, checklists and sourced references |
get_crew | One crew: its members in full, and the install command for each integration it names |
get_integration | One pinned install recipe for third-party software, with the secrets it needs and what they reach |
Without an MCP client, nothing above is required:
npx -y forgeprint get ts-http-service --agent cursor --options framework=hono
That writes the files that agent reads, and the recipe with your options resolved — the same answer the tools give, because it is the same code (ADR 0013). It reads the published catalog, or a checkout when you are in one. The catalog is also published as JSON at forgeprint.github.io/forgeprint/index.json and as llms.txt.
Forgeprint replies in English. Your agent presents it in your language: the tools take a locale hint and hand it back, so nothing in the catalog has to be translated. See ADR 0004.
npx forgeprint validate # in a checkout of any Forgeprint catalog
npx -y forgeprint-mcp # the MCP server, over stdio
To work on the catalog itself:
git clone https://github.com/forgeprint/forgeprint.git
cd forgeprint pnpm install pnpm run build pnpm forgeprint validate
| Command | What it does |
|---|---|
pnpm forgeprint validate | Schema, taxonomy, required files, and the catalog-wide rules |
pnpm forgeprint build-index | Regenerate docs/index.json |
pnpm forgeprint build-schema | Regenerate schema/manifest.schema.json |
pnpm forgeprint build-codeowners | Regenerate .github/CODEOWNERS from the manifests |
pnpm forgeprint lint-setup | Check a setup recipe: numbering, verification, pinning, safety |
pnpm forgeprint similarity | Duplicate report against every other blueprint |
Every pipeline step is a command you can run locally. Hosted CI is a convenience, never a dependency: the workflows call these same commands, the generated index is committed to the repository, and GitHub Pages serves it straight from the branch. When Actions is unavailable, nothing stops. See ADR 0002.
blueprints/<slug>/ one folder per blueprint — the unit of contribution
skills/ blueprint-author and blueprint-review schema/ manifest schema and the controlled taxonomy packages/cli/ forgeprint validate / build-* / similarity / lint-setup packages/mcp-server/ the MCP server (npx forgeprint-mcp) packages/site/ the static GitHub Pages site, generated into docs/ docs/ index.json, the ADRs, and the published site
official blueprints, the blueprint-author and blueprint-review skills, the similarity report and the setup lint.forgeprint-mcp.validate on every push and pull request, setup-test on the recipes. forgeprint validate checks the skill format the distribution tools read, so npx skills add and gh skills install agree with it (ADR 0006).A "times resolved" counter is not planned. It would mean the serve
冒頭だけを表示しています。続きはリポジトリで読めます