Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Model Context Protocol (MCP) server for programmatic PowerPoint creation and editing
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"chatppt": {
"command": "npx",
"args": [
"-y",
"@jparkerdiamond/chatppt"
]
}
}
}Run this in your terminal
claude mcp add chatppt -- npx -y @jparkerdiamond/chatpptPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"chatppt": {
"command": "npx",
"args": [
"-y",
"@jparkerdiamond/chatppt"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"chatppt": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@jparkerdiamond/chatppt"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account ParkerDiamond, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.2.0) reached the registry 40 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Zendesk
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
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.
Zendesk MCP Pack — tickets, users, organizations via OAuth.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
ChatPPT is a Model Context Protocol (MCP) server for programmatic, AI-assisted PowerPoint creation and editing. Built on Node.js 20+ and @office-kit/pptx, ChatPPT exposes a safe, structured, resource-oriented CRUD API over stdio for connected LLMs in Visual Studio Code and other MCP-compatible clients.
presentations/ .pptx..chatppt/registry.json.@office-kit/pptx-preview..vscode/mcp.json)To use ChatPPT in your VS Code workspace, add or update .vscode/mcp.json in the root of your workspace:
{
"servers": { "chatppt": { "type": "stdio", "command": "node", "args": ["${workspaceFolder}/dist/index.js"] } } }
npx ExecutionWhen running via npx or published binary, ChatPPT can be configured to target a specific workspace using the --workspace flag or environment variables:
{
"servers": { "chatppt": { "type": "stdio", "command": "npx", "args": ["-y", "@jparkerdiamond/chatppt", "--workspace", "${workspaceFolder}"] } } }
The npm package includes the portable create-deck-skeleton Agent Skill at skills/create-deck-skeleton/SKILL.md. MCP clients do not automatically load agent skills when connecting to a server. To use the skill, install or copy that directory into the skill-discovery location supported by your agent host, such as .github/skills/, .agents/skills/, or .claude/skills/. The skill uses ChatPPT's MCP tools and does not depend on a particular operating system or editor.
ChatPPT operates on a deterministic workspace root resolved in the following priority order:
--workspace or -w CHATPPT_WORKSPACE_ROOT or WORKSPACE_ROOTprocess.cwd() (current working directory) /presentations/ .pptx /.chatppt/registry.json^[a-zA-Z0-9_-]+$. Absolute paths or relative paths attempting directory traversal (..) outside the workspace root are caught and rejected with ValidationError..pptx presentations are detected and rejected.deck_*)deck_create: Create a new blank presentation deck.deck_import: Import an existing PowerPoint file into the managed workspace and register its slides.deck_list: List all managed decks in the workspace.deck_read: Read metadata and slide/collection list for a deck.deck_update: Update deck metadata (title) with optional optimistic revision check (expectedRevision).deck_delete: Permanently delete a deck and its .pptx file.deck_validate: Run diagnostic invariant checks across PPTX content and registry metadata.slide_*)slide_create: Add one or multiple slides in batch (supports title and notes).slide_list: List slides in presentation order with 0-based position indexes.slide_read: Read slide metadata and its element listing.slide_render: Render a slide to a PNG image preview for visual feedback. Accepts an optional width in pixels, defaulting to 1280, and returns an MCP image content item.slide_update: Update slide title and speaker notes in batch.slide_delete: Permanently delete slides and clean up collection references.slide_move: Move a slide or reorder slides by providing a slideOrder array.slide_duplicate: Duplicate a slide with new stable IDs for the slide and all elements.slide_collection_*)slide_collection_create: Create a named ordered group of existing slides.slide_collection_list: List collections in a presentation.slide_collection_read: Read collection details and slide membership.slide_collection_update: Rename a collection or replace slide membership.slide_collection_delete: Delete a collection without deleting the slides.element_*)element_create: Create text boxes, preset shapes, lines, tables, charts, or images in batch (supports optional clientId correlation).element_list: List all elements on a slide in z-index order.element_read: Read element metadata and styling properties.element_update: Update position, size, text, fill, font, size, bold, italic, text color, stroke, and alignment in batch.element_delete: Delete elements from a slide in batch.element_reorder: Adjust element z-index (bringToFront, sendToBack, bringForward, sendBackward).Call slide_render with the deck and slide UUIDs. The response includes a base64-encoded image/png content item that MCP clients can display directly:
{
"deckId": " ", "slideId": " ", "width": 1280 }
The renderer is a deterministic approximation of PowerPoint output and runs in Node.js without a headless browser.
npm install
npm run build
npm test
npm run dev
The publish.yml GitHub Actions workflow stages a package when a matching v* tag is pushed. The package must already exist on npm. The workflow uses GitHub OIDC through npm trusted publishing and does not require an npm token. A staged package is not public until a maintainer reviews and approves it with 2FA on npm.
Configure the npm package's trusted publisher with GitHub Actions, repository ParkerDiamond/ChatPPT, workflow filename publish.yml, and the npm stage publish action enabled. The staging job uses Node.js 24 and npm 11.15.0 or later.
The same publish.yml workflow publishes server.json to the MCP Registry when a v* version tag is pushed. It authenticates with GitHub OIDC and does not require a registry secret. The registry job waits for npm staging, but MCP Registry validation requires the referenced npm version to be publicly available. If npm approval is still pending when the workflow runs, approve the staged npm release and rerun the failed registry job.
MIT