Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Beschreibung vom Entwickler (englisches Original)
Edit real .xlsx files with your agent: live formulas, and you review every change before it saves.
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
Du brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein
{
"mcpServers": {
"gridpath": {
"command": "npx",
"args": [
"-y",
"gridpath",
"mcp"
]
}
}
}Führe das in deinem Terminal aus
claude mcp add gridpath -- npx -y gridpath mcpIn .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"gridpath": {
"command": "npx",
"args": [
"-y",
"gridpath",
"mcp"
]
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"gridpath": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"gridpath",
"mcp"
]
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Dieser Server läuft auf deinem Computer, und ChatGPT kann sich nur mit Servern im Internet verbinden. Wähle eine andere App.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Läuft auf deinem Computer; die Tool-Liste erscheint nach der Installation in deiner KI-App.
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 7. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto pixelsmasher13 bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieser Server läuft auf deinem Computer; es gibt keinen Endpunkt im Internet
Läuft auf deinem Computer und nutzt stattdessen lokale Einstellungen
Läuft auf deinem Computer; Tool-Listen können wir nur von Endpunkten im Internet lesen
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 1 von 1 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Die Registry nennt keinen erforderlichen Schlüssel, manche Server bitten dich aber bei der ersten Nutzung, dich anzumelden.
Er läuft auf deinem Computer. Deine KI-App startet ihn bei Bedarf, und die Daten laufen nicht über die Server des Entwicklers (außer der Server ruft selbst einen Onlinedienst auf).
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (0.5.0) kam vor 10 Tagen in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Außerdem brauchst du Node.js auf deinem Computer.
In derselben Kategorie: Spec Driven Development, Remote Desktop Commander, Systemdox
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
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.
Your architecture in your agents' context: checks, specs, ADRs and docs over MCP, at write time.
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
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.
Nur der Anfang wird gezeigt; den Rest findest du im Repo