deckrun-free
Generates PDF slide decks from Markdown using any MCP-compatible AI client. Free, no authentication, max 10 slides, output URL valid 90 days.
README
Deckrun Free — MCP Server
Generate PDF slide decks from Markdown using any MCP-compatible AI client. Free. No authentication required.
- API:
https://free.agenticdecks.com/free/generate - Max: 10 slides, 50 KB Markdown
- Output: Public PDF URL, valid 90 days
Install
Via Smithery (easiest — auto-configures your client)
# Claude Desktop
npx @smithery/cli install @agenticdecks/deckrun-free --client claude
# Cursor
npx @smithery/cli install @agenticdecks/deckrun-free --client cursor
# VS Code (GitHub Copilot)
npx @smithery/cli install @agenticdecks/deckrun-free --client vscode
# OpenAI Codex CLI
npx @smithery/cli install @agenticdecks/deckrun-free --client codex
Server page: https://smithery.ai/servers/agenticdecks/deckrun-free
Google Antigravity
Add to ~/.gemini/antigravity/mcp_config.json (no local Python install needed):
{
"mcpServers": {
"deckrun-free": {
"serverUrl": "https://free.agenticdecks.com/mcp/"
}
}
}
Manual install
pip install mcp requests
Manual Setup
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"deckrun-free": {
"command": "python",
"args": ["/path/to/deckrun_mcp_server.py"]
}
}
}
Restart Claude Desktop. Then ask: "Create a 6-slide deck on quantum computing."
Cursor
Edit .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"deckrun-free": {
"command": "python",
"args": ["/path/to/deckrun_mcp_server.py"]
}
}
}
VS Code (GitHub Copilot)
In .vscode/settings.json:
{
"github.copilot.chat.mcp.servers": {
"deckrun-free": {
"command": "python",
"args": ["/path/to/deckrun_mcp_server.py"]
}
}
}
Tools
| Tool | Description |
|---|---|
get_slide_format |
Fetches live Deckrun slide format spec. Call this first. |
generate_slide_deck |
Converts Deckrun Markdown to PDF. Returns url, slides, warnings. |
Resources
| URI | Content |
|---|---|
deckrun-free://skill |
OpenClaw/ClawHub skill YAML for agent registries |
deckrun-free://openapi |
Live OpenAPI spec for /free/generate |
How it works
Claude (in your IDE)
→ calls get_slide_format → fetches live schema from agenticdecks.com
→ writes Deckrun Markdown in context window
→ calls generate_slide_deck(markdown)
→ POST https://free.agenticdecks.com/free/generate
← {"url": "...", "slides": 6, "warnings": [], "schema_version": "deckrun.v1"}
← "Your PDF is ready: https://..."
Links
- agenticdecks.com — product overview
- free.agenticdecks.com — web UI
- API spec
- Community / paid plans
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.