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)
Edit real .xlsx files with your agent: live formulas, and you review every change before it saves.
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": {
"gridpath": {
"command": "npx",
"args": [
"-y",
"gridpath",
"mcp"
]
}
}
}ターミナルでこれを実行します
claude mcp add gridpath -- npx -y gridpath 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": {
"gridpath": {
"command": "npx",
"args": [
"-y",
"gridpath",
"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": {
"gridpath": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"gridpath",
"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7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 pixelsmasher13 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(0.5.0)がレジストリに届いたのは11 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, LexPact UK Contracts
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.
Generate UK-law contracts: NDA, service, freelance, recruiter terms of business, IR35.
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。
Real Excel files, in your web app and in your agent. Open the .xlsx your users already have, keep every formula live at full size, let AI edit it with review, and save back the same file.
| In your web app | In your coding agent | |
|---|---|---|
| Install | npm install gridpath | claude mcp add gridpath -- npx -y gridpath mcp |
| What you get | An embeddable spreadsheet: a canvas grid over a Rust/WebAssembly engine in a Web Worker, in-place .xlsx saves, and agent tools for your own model | An MCP server for Claude Code, Claude Desktop, Cursor, Codex: the agent edits files on disk and you review every change before it is saved |
| Docs | In your web app | In your coding agent |
Both run the same engine (a fork of IronCalc): real formulas evaluated in process, and saves that patch the original file so untouched parts come back byte-identical. Recalculated formulas and supported chart data caches carry current values; chart definitions remain native Excel XML.
npm install gridpath react react-dom
React and React DOM are peer dependencies. Your app doesn't have to use React: createSpreadsheet mounts the spreadsheet into any element.
import { Spreadsheet } from "gridpath";
(sheetRef.current = sheet)} onError={(err) => console.error(err.code, err.message, err.hint)} /> ;
Without React:
import { createSpreadsheet } from "gridpath";
const sheet = await createSpreadsheet(document.getElementById("sheet")!, { file: await file.arrayBuffer() }); sheet.setCell("Sheet1", "B2", "=SUM(A1:A10)"); console.log(await sheet.getCell("Sheet1", "B2")); // { value: 55, formula: "=SUM(A1:A10)" } const xlsx = await sheet.save(); // Uint8Array
createSpreadsheet resolves once the workbook is open. If it can't open it rejects with a GridPathError and leaves the element empty.
No configuration is needed. This was tested on Next.js 16 with React 19, with Turbopack and with webpack, in next dev and in production builds.
"use client"). The page around it can stay a server component.gridpath/agent works in a route handler.examples/nextjs-demo is a complete app. Each user has a list of workbooks saved to the app's own API: app/api/books/[[...path]]/route.ts holds the REST routes httpStore calls, with auth. Each workbook has its own URL. The example shows:
Keyboard shortcuts (⌘B, ⌘Z, ⌘S…) work in the grid. toolbar={false} hides the toolbar.
fileMenu={false} removes those entries when your app has its own list..xlsx, a separate button from Save.sheet.ai. Each change shows what it did ("D2: empty → =C2/B2-1") and where, with Accept and Reject buttons. Clicking a change shows its cells.reviewPanel={false} turns the panel off if your app has its own review UI.A spreadsheet shows one workbook at a time. You identify a workbook by its documentId, which defaults to fileName. Together with a store, the ID is how a workbook is loaded:
<Spreadsheet store={store} documentId={book.id} fileName={book.name} />
The spreadsheet opens the stored state for that ID. If you also pass a file, the stored state wins only when it was saved from that same file; otherwise file opens. With nothing stored and no file, the workbook starts blank.
Switching workbooks can be done in two ways:
key={book.id}, as the Next.js example does with a page per workbook.| When you open another workbook… | |
|---|---|
| AI changes are waiting for review | It rejects with PendingChangesError. Accept or reject them first. |
There are unsaved edits and a store or onSave | They are saved first. |
| The save fails or nothing is set up to save to | It rejects with UnsavedChangesError. Pass { discardUnsaved: true } to drop the edits. A remote store's failed save is not counted as a failure here: those edits are kept in this browser. |
| The new file can't be opened | It rejects with unsupported-file or malformed-file, and the previous workbook stays open. Plainly wrong files (empty, old .xls, a PDF or image) are refused before anything changes. |
The File menu follows the same rules and asks the user before it discards anything.
Cleaning up.
createSpreadsheet only). If there are edits that aren't saved yet, they are saved first. This covers a client-side navigation, which fires no beforeunload. Then the engine's worker stops. From then on, every call on the old sheet object fails with not-ready.file, open() and the File menu also take CSV and other delimited text. It opens as a new workbook, which saves as .xlsx: sales.csv becomes sales.xlsx, with one sheet named sales, and the toolbar says so.
sep=; first line is honoured. In semicolon files a comma is the decimal point (1.234,5 is 1234.5).TRUE/FALSE, and = formulas, which calculate. A formula that doesn't parse stays text.Text that isn't a table (.json, .xml, .html, .md…) is refused with unsupported-file. A 17 MB CSV (2 million cells) opens in 7 to 10 seconds in Chromium on a recent Mac.
Saving happens in three ways:
autosave (milliseconds), or turn it off with false.Each save writes the workbook to the store and calls onSave. Watch it with onStatusChange or getStatus():
state | The toolbar says | |
|---|---|---|
"saved" | "Saved in this browser" / "Saved to your account" | savedAt, and where: the store's label. |
"unsaved" | "Unsaved changes" | An autosave is coming. |
"saving" | "Saving…" | |
"review" | "Review 2 AI changes to save" | pending. Saving waits for the user to accept or reject the AI's changes. |
"error" | "Couldn't save · Retry", or "Saved in this browser only · Retry" | code, message and hint. keptLocally is set when the edits are safe in this browser, and retryAt when autosave will try again. |
"idle" | (nothing) | A fresh workbook, or no saving set up. |
save() and saveBlob() return the bytes without touching the store, for an upload of your own.
By default, everything is kept in the user's browser (IndexedDB) by browserStore(). Saves within five minutes of each other share one version. The newest 20 versions are kept as they are, then one per day for 30 days. Tune this with browserStore({ checkpointMinutes, keepRecent, keepDays }).
To save to the signed-in user's account, point httpStore at your API:
import { httpStore } from "gridpath";
const store = httpStore({ url: "/api/books", // Called before every request, so a refreshed token is picked up. Leave it // out with cookie sessions. headers: async () => ({ Authorization: Bearer ${await getToken()} }), });
;
The routes it calls, all relative to url. Ids are URL-encoded:
| Request | Response |
|---|---|
PUT /{id}?name=…&source=…[&checkpoint=1], with the .xlsx as the body | Any 2xx. source fingerprints the file the workbook was opened from. checkpoint asks for a version of its own (before and after a restore). |
GET /{id} | The .xlsx, with headers: X-Workbook-Name (percent-encoded), X-Workbook-Saved-At (an ISO time), X-Workbook-Source. A 404 when there's none. |
GET / | [{ id, name, savedAt, size }], newest first (the Recent list). |
GET /{id}/versions | [{ id, savedAt, size }], newest first. A 404 when you keep no history. |
GET /{id}/versions/{versionId} | That version's .xlsx. |
DELETE /{id} | Any 2xx. |
When the backend can't be reached or answers with an error, the user's edits are not lost:
keptLocally: true.If the backend can't be reached when a workbook *opens*, the spreadsheet shows the error with Try again.
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