SlideSpeak MCP Server
Create presentations and PowerPoint slides using AI. Generate professional decks from content descriptions.
- Maintained by
- SlideSpeak
- Hosting
- Hosted endpoint, or run it locally
- Authentication
- API key
- Last checked
How to connect the SlideSpeak MCP server
Pick your AI client and paste the snippet. Swap the YOUR_… placeholders for your own values. New to this? Our guide to how MCP clients and servers fit together explains what each piece does.
Claude Code
claude mcp add --transport http slidespeak https://mcp.slidespeak.co/mcp \
--header 'Authorization: Bearer YOUR_API_KEY' Claude Desktop and claude.ai
Custom connectors in Claude accept OAuth or no-auth servers only.
This server expects an API key in a header, so use Claude Code,
Cursor or VS Code instead, or the local setup below. Cursor
{
"mcpServers": {
"slidespeak": {
"url": "https://mcp.slidespeak.co/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
} VS Code
{
"servers": {
"slidespeak": {
"type": "http",
"url": "https://mcp.slidespeak.co/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
} + − Run it locally instead
Claude Code
claude mcp add --env SLIDESPEAK_API_KEY=YOUR_API_KEY --transport stdio slidespeak \
-- docker run -i --rm -e SLIDESPEAK_API_KEY slidespeak/slidespeak-mcp:latest Claude Desktop
{
"mcpServers": {
"slidespeak": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"SLIDESPEAK_API_KEY",
"slidespeak/slidespeak-mcp:latest"
],
"env": {
"SLIDESPEAK_API_KEY": "YOUR_API_KEY"
}
}
}
} Fully quit and reopen Claude Desktop after saving.
Full Claude Desktop setup guide →Cursor
{
"mcpServers": {
"slidespeak": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"SLIDESPEAK_API_KEY",
"slidespeak/slidespeak-mcp:latest"
],
"env": {
"SLIDESPEAK_API_KEY": "YOUR_API_KEY"
}
}
}
} VS Code
{
"servers": {
"slidespeak": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"SLIDESPEAK_API_KEY",
"slidespeak/slidespeak-mcp:latest"
],
"env": {
"SLIDESPEAK_API_KEY": "YOUR_API_KEY"
}
}
}
} Frequently asked questions
What is the SlideSpeak MCP server?
It is a Model Context Protocol (MCP) server — a small piece of software that gives AI assistants like Claude a secure, governed connection to SlideSpeak. Create presentations and PowerPoint slides using AI. Generate professional decks from content descriptions.
Is there an official SlideSpeak MCP server?
Yes. The SlideSpeak MCP server is an official integration, maintained by the vendor or the Model Context Protocol project, which makes it the safest default for business use. It is maintained by SlideSpeak.
Is the SlideSpeak MCP server hosted, or do I run it myself?
Both. SlideSpeak runs a hosted endpoint at https://mcp.slidespeak.co/mcp, so most people just paste that URL into their AI client. You can also run the server locally with docker, supplying your own credentials.
Do I need an API key for the SlideSpeak MCP server?
Yes. The hosted server expects an API key from your SlideSpeak account, sent in the Authorization header. Store it in your client's secret settings rather than pasting it into shared config files.
What can an AI assistant actually do with SlideSpeak?
Through this server an assistant can work with presentations, powerpoint, slides, templates — reading from and acting on SlideSpeak directly instead of you copy-pasting between windows. What you allow it to do is controlled by the permissions you grant.
How do I set this up for my business?
The setup section above has copy-paste config for Claude Code, Claude Desktop, Cursor and VS Code. Once it is running against real systems, the question becomes what catches it when it acts wrongly, which is what Crox's Safety Diagnostic looks at.
New to MCP? Start with our plain-English guide to the Model Context Protocol or see how to connect AI to your business tools without writing code .
Already running this in production?
An agent with a live connection to your tools is a model that can act. Crox looks at what catches it when it acts wrongly: the layers around it, who can stop it, and where a near miss gets reported. Two days, one team, one model.