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)
Your writing voice measured across 45 attributes; drafts in that voice, scored against it.
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。
Authorization「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
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。
このアドレスはリクエストの header にキーが必要ですが、コネクタを追加するメニューでは設定できません。代わりにClaude Code、Cursor、VS Codeを使ってください。
ターミナルでこれを実行します
claude mcp add --transport http scriptgrain https://mcp.scriptgrain.com/mcp --header 'Authorization: your-value'動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"scriptgrain": {
"url": "https://mcp.scriptgrain.com/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}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": {
"scriptgrain": {
"type": "http",
"url": "https://mcp.scriptgrain.com/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}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。
このアドレスはリクエストの header にキーが必要ですが、コネクタを追加するメニューでは設定できません。代わりにClaude Code、Cursor、VS Codeを使ってください。
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。
Authorization 秘密 HTTP header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。
このサーバーのツール一覧はまだ読み取っていません。エンドポイントは順番にチェックしています。
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7日にチェック
レジストリ名はドメイン scriptgrain.com で確認済みです(レジストリがドメインの所有を確認しています)
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
まだチェックしていません。エンドポイントは順番にチェックしています
まだチェックしていません。エンドポイントは順番にチェックしています
まだチェックしていません。エンドポイントをチェックするときにツール一覧を読み取ります
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。
入力が必要なもの:Authorization
作者のクラウドで動きます。インストール不要でインターネット経由でつながりますが、送った内容は作者のサーバーを通ります。
GitHubリポジトリの最終更新は–、最新バージョン(1.23.1)がレジストリに届いたのは22 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。URLでつながるので、リモートMCPサーバーに対応したアプリ(開発者モードのChatGPTなど)でも使えます。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, Python 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.
Local-only Python MCP server for the Files.com API.
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。
ScriptGrain makes ChatGPT, Claude and the rest better at being you. This repository is the public setup guide for its remote MCP server: connect it to Claude, ChatGPT, Cursor or any MCP client, and your assistant can build a voice profile from your own writing, draft in that voice, and score any text against it.
https://mcp.scriptgrain.com/mcp (streamable HTTP, answered as plain JSON; legacy SSE at https://mcp.scriptgrain.com/sse)https://mcp.scriptgrain.com/try needs no key or sign-in: start_session gives your assistant a 7-day guest session that builds one voice profile and scores text against it, then hands you a link to keep it in a free accountAuthorization: Bearer sg_live_...This repository is a guide: documentation and client configuration only. It contains no ScriptGrain source code; the application and the MCP server are private and hosted by ScriptGrain, so there is nothing to install or run.
A voice profile is built from writing you have already done: 45 attributes in eight groups (lexical, syntax, tone and register, rhetoric, punctuation and format, function words, content patterns, quirks and cadence). Every draft is scored from 0 to 1 against the profile: on-voice drafts typically score 0.85 to 0.95, partial matches 0.5 to 0.8, and clearly off-voice text below 0.45. Each attribute has its own page at https://scriptgrain.com/attributes.
You need a ScriptGrain account (free): https://scriptgrain.com/auth?tab=signup&source=github_mcp
https://mcp.scriptgrain.com/mcp.The connector mints its own API key, named after the client, in your ScriptGrain account. Revoke it in Settings, API, and the access ends.
With OAuth (Claude Code opens the sign-in when you run /mcp):
claude mcp add --transport http scriptgrain https://mcp.scriptgrain.com/mcp
With an API key:
claude mcp add scriptgrain https://mcp.scriptgrain.com/mcp \
--transport http --header "Authorization: Bearer sg_live_ "
Project-scoped config for a shared repository: config/claude-code.mcp.json (OAuth, so no key is committed).
Where your ChatGPT plan offers connectors: Settings, then Connectors, then Add custom connector, with the URL https://mcp.scriptgrain.com/mcp, and sign in with your ScriptGrain account when the consent page opens. Where connectors are not available on your plan, the free prompt builder at https://scriptgrain.com/works-with/chatgpt writes a one-page system prompt from your writing for Custom instructions instead.
Add a remote MCP server named scriptgrain with the URL https://mcp.scriptgrain.com/mcp and complete the sign-in when the consent page opens: config/cursor.mcp.json. Where a client cannot do OAuth, send the key as a header instead: config/cursor.mcp.with-key.json. Keep a file that holds a key out of version control.
Use https://mcp.scriptgrain.com/mcp with OAuth or the Authorization: Bearer header. Every POST is answered as plain JSON, never as an event stream, so clients and proxies that only handle request and response work too. Send the Mcp-Session-Id header from the initialize response on every later call.
41 tools, listed from the server's own registrations (server 1.23.1). The tools that delete or overwrite (delete_memory, forget_piece, edit_memory, remove_monitor_url, set_voice_brain, delete_brief_template) are marked destructive, so your client can ask before running them. Credits are from your ScriptGrain plan; "free" means no credit is used.
Drafts, polish and humanise are priced by length: up to 5,000 words 1 credit, up to 10,000 words 2, up to 15,000 words 3 (the most one piece can be). A draft over 4,000 words, or a polish or humanise over 3,000 words, runs in the background: the tool returns at once with a job, and get_job shows its progress until it has succeeded (about a minute per 2,000 words). Credits are charged as the words are delivered, never above the tier asked for.
| Tool | What it does | Cost |
|---|---|---|
list_profiles | Lists the voice profiles your key can use, with status, confidence score and sample count | Free |
create_profile | Builds a voice profile from 1 to 20 samples of your own writing (3+ pieces and 3,000+ words gives a confident profile); runs for about 1 to 3 minutes | 1 extraction slot |
get_profile | A profile's status and, once complete, its narrative description and all 45 attributes | Free |
mimic_brand | Builds a profile from a public brand website (up to 8 pages); asks for your explicit consent first | 1 brand-mimic credit |
| Tool | What it does | Cost |
|---|---|---|
create_outline | An outline for a long-form piece, to review before drafting | Free |
generate_content | A draft in your measured voice in one of 16 content types, up to 15,000 words, with its voice-match score; 1 to 3 variants (2 and 3 up to 4,000 words); over 4,000 words it is written in the background | Per variant: 1 credit up to 5,000 words, 2 up to 10,000, 3 up to 15,000 |
check_voice_match | Scores any text against a profile, with the per-feature numbers behind the score | Free |
compare_voice | No profile needed: scores up to three pieces (text or URL) against a main piece | Free |
polish | Revises a draft toward a voice-match target (default 0.9), up to 3 passes; over 3,000 words it runs in the background | 1 credit up to 5,000 words, 2 up to 10,000, 3 up to 15,000; free if the draft already passes |
humanize | Rewrites text (or a saved draft) to remove measurable machine-writing tells while keeping every fact, up to 3 passes; over 3,000 words it runs in the background | 1 credit up to 5,000 words, 2 up to 10,000, 3 up to 15,000; free if the text already passes (up to 3,000 words) |
ai_detect | Stylometric human-vs-AI reading of any text of 50+ words | Free |
rewrite_page | Rewrites a public web page's copy in your voice, block by block; prices, legal lines and button labels are left alone | 1 credit per 1,500 words; paid plans |
save_edit | Saves your final edit of a draft, so the profile learns from the difference | Free |
list_generations | Lists past drafts with their scores | Free |
get_generation | Fetches one past draft in full (while a long draft is being written, the part delivered so far) | Free |
get_job | Progress of a background job (a long draft, polish or humanise): sections done, words written, credits charged, and the result once it has succeeded | Free |
list_draft_versions | A draft's earlier texts, newest first: every edit, polish, humanise or redraft keeps the text it replaced | Free |
restore_draft_version | Puts an earlier version back; the text it replaces is kept too, so it can be undone | Free |
list_brief_templates | Your saved briefs (and your team's), to start from with template_id on create_outline or generate_content | Free |
save_brief_template | Saves a brief (format, topic, angle, audience, register, key points, length) for next time | Free |
delete_brief_template | Deletes a saved brief | Free |
| Tool | What it does | Cost |
|---|---|---|
get_memory | The ideas, claims, stories and frameworks your writing has covered, each with a verbatim quote | Free |
sync_memory | Indexes new drafts and samples into the memory | Free |
check_novelty | Checks a brief against the memory: repeats, builds on, or new, with grounded angles | Free |
what_next | Five angles that build on what you keep saying | Free |
add_to_memory | Adds a published piece by pasted text or URL (60+ words), or one memory stated directly (memory, with an optional kind and topic) | Free |
set_repeat_policy | Whether drafts avoid restating earlier arguments (the default) or may repeat them | Free |
list_brains | Lists the memories (brains) a voice may use and which voices share each | Free |
set_voice_brain | Moves a voice to another brain, or back to its own | Free |
edit_memory | Changes one memory: its words, its kind, or its topic | Free |
delete_memory | Deletes one memory | Free |
forget_piece | Forgets a whole piece and every memory taken from it | Free |
| Tool | What it does | Cost |
|---|---|---|
get_voice_monitor | The pages being watched, the latest run's scores and the previous run | Free; paid plans |
add_monitor_url | Watches a public page (Writer and Operator 5 pages, Studio 15, Agency 50) | Free; paid plans |
remove_monitor_url | Stops watching a page; past results are kept | Free |
run_voice_monitor | Runs this month's check now (one run per profile per month; the scheduled run is on the 1st) | Free |
| Tool | What it does | Cost |
|---|---|---|
list_companies | Lists your company or product profiles, used to ground drafts in real facts | Free |
create_company | Creates one from a URL, freeform notes or fields; only claims the pages make | Free (reading a site by URL needs a paid plan) |
| Tool | What it does | Cost |
|---|---|---|
get_billing | Plan, remaining credits and renewal date | Free |
get_invoice | The latest invoice with a PDF link | Free |
upgrade_plan | A Stripe-hosted link to upgrade or manage the plan; nothing is charged through the connector | Free |
write_in_my_voice: draft a piece, report its score, iterate, and save the final edit.build_my_voice_profile: gather your own writing, create the profile, and walk through the result.mimic_brand needs your explicit consent to analyse a website's writing.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