slidev-mcp

slidev-mcp

Enables AI assistants to create and update presentations via Slidev, with hosted slides that can be shared via a permanent URL.

Category
Visit Server

README

<p align="center"> <img src="docs/public/slidev-mcp-logo.png" width="80" alt="Slidev MCP"> </p>

<h1 align="center">Slidev MCP</h1>

<p align="center"> Ask your AI to create a presentation. Get a shareable link. </p>

<p align="center"> <a href="https://slidev-mcp.org">Docs</a> · <a href="#quick-start">Quick Start</a> · <a href="#supported-clients">Clients</a> · <a href="#themes">Themes</a> </p>

<p align="center"> <a href="https://github.com/joelbarmettlerUZH/slidev-mcp/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/joelbarmettlerUZH/slidev-mcp/ci.yml?label=tests&labelColor=212121" alt="Tests"></a> <a href="LICENSE.md"><img src="https://img.shields.io/badge/license-FSL--1.1--ALv2-blue?labelColor=212121" alt="License"></a> </p>

<p align="center" width="100%"> <img src="docs/public/demo-readme.webp" width="80%" alt="Slidev MCP demo — creating a presentation with AI"> </p>


How It Works

  1. Connect your AI assistant to mcp.slidev-mcp.org/mcp
  2. Ask it to create a presentation on any topic
  3. Share the link it gives you — it works in any browser, no login required

Your slides are hosted and ready to present. Bookmark them, send them to a colleague, or open them on your phone.

Quick Start

Claude Code

claude mcp add --scope user slidev-mcp --transport streamable-http https://mcp.slidev-mcp.org/mcp

That's it. Start a conversation and ask Claude to make a presentation.

Claude Desktop / claude.ai

Add mcp.slidev-mcp.org/mcp as a custom connector in Settings > Connectors.

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "slidev-mcp": {
      "url": "https://mcp.slidev-mcp.org/mcp"
    }
  }
}

Other Clients

Any MCP client that supports streamable HTTP works with:

https://mcp.slidev-mcp.org/mcp

See client setup guides for Windsurf, VS Code, JetBrains, Zed, Opencode, Gemini CLI, and ChatGPT.

What You Can Do

  • Create presentations — describe what you want, pick a theme, get slides
  • Update slides — ask for changes and the same URL updates in place
  • Browse themes — ask to see the theme gallery or let the AI pick one for you
  • Learn Slidev — the AI reads the Slidev docs automatically and uses theme-specific layouts and components

Sharing Your Slides

Every presentation gets a permanent URL like:

https://slides.slidev-mcp.org/slides/abc123-def456/
  • Open it in any browser — no login, no app required
  • Bookmark it for later
  • Send it to anyone
  • Present directly from the browser (press f for fullscreen)
  • Slides stay available for 30 days after your session ends

While your session is active, you can keep updating the same presentation. Once you disconnect, the slides become a permanent snapshot.

Themes

24 pre-installed themes to choose from:

Official: default, seriph, apple-basic, bricks, shibainu

Community: academic, cobalt, dracula, eloc, field-manual, frankfurt, geist, neocarbon, neversink, nord, penguin, purplin, scholarly, swiss-ai-hub, the-unnamed, unicorn, vibe, vuetiful, zhozhoba

Ask your AI to "show me the themes" for a visual gallery, or describe a style like "something dark and modern" and let it pick.

Supported Clients

Client Type Setup
Claude Code CLI One command
Claude Desktop / claude.ai Desktop / Web Custom connector
Cursor IDE JSON config
Windsurf IDE JSON config
VS Code (Copilot) IDE JSON config
JetBrains IDEs IDE JSON config
Zed IDE JSON config
Opencode CLI JSON config
Gemini CLI CLI JSON config
ChatGPT Web / Desktop JSON config

Self-Hosting

Slidev MCP can be self-hosted on your own server. See the deployment guide for Docker Compose setup with Let's Encrypt TLS.

Development

make install          # Install Python dependencies
make docker-dev-up    # Start Postgres + Builder
make serve            # Run MCP server locally
make pr-ready         # Lint + format + test

License

FSL-1.1-ALv2 — Functional Source License, converting to Apache 2.0 after two years.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured