ppt-generator-mcp
MCP server for generating PowerPoint presentations, supporting AI-generated or manual slide creation with 21 layouts, rendering via pptxgenjs, and uploading to OCI Object Storage.
README
ppt-generator-mcp
MCP server for generating PowerPoint presentations, exposed over HTTP (JSON-RPC). Decks can be AI-generated from a topic or built slide-by-slide, rendered with pptxgenjs, and uploaded to OCI Object Storage.
Tools
| Tool | Description |
|---|---|
create_deck |
Create a deck — auto-generate slides from a topic via AI, or pass a manual slides array |
get_deck |
Get full deck data (all slides) |
add_slide |
Add a slide to an existing deck |
update_slide |
Update fields on an existing slide |
delete_slide |
Remove a slide |
reorder_slides |
Change slide order |
21 layouts available: cover, section, icon-point, icon-list, big-number, quote, image-text, comparison, three-icons, focus, timeline, process, stats-grid, pros-cons, agenda, team, gallery, full-image, chart, table, contact, closing.
Setup
npm install
npm run build
npm start
Copy .env.example to .env (or create one) with your OCI GenAI + Object Storage config:
| Variable | Description |
|---|---|
OCI_GENAI_COMPARTMENT_ID |
OCI compartment for GenAI inference (required) |
OCI_OS_NAMESPACE / OCI_OS_BUCKET |
Object Storage bucket for generated decks (required) |
OCI_CONFIG_FILE / OCI_CONFIG_PROFILE |
OCI CLI config (default ~/.oci/config, DEFAULT) |
USE_RESOURCE_PRINCIPAL |
Use instance/resource principal auth instead of the config file |
UNSPLASH_ACCESS_KEY / PEXELS_API_KEY |
Stock photo sources for image slides |
PORT |
Server port (default 8086) |
API_KEY |
Optional key required on /mcp requests |
Endpoints
| Method | Path | Description |
|---|---|---|
GET |
/health |
Health check |
GET |
/test-genai |
Verify OCI GenAI connectivity |
POST |
/mcp |
JSON-RPC endpoint (MCP protocol) |
Docker
docker build -t ppt-generator-mcp .
docker run -p 8086:8086 --env-file .env ppt-generator-mcp
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.