presentations-ai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | Yes | Your Presentations.AI API key from https://presentations.ai/dashboard |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_presentation_from_topicA | Generate a full AI-powered presentation from a topic or brief. Use when the caller has a subject line, headline, or short brief and wants a complete deck. Returns a job ID for async processing; poll check_job_status until status is completed, then use the returned docurl. For a single hero slide instead of a deck, use create_single_slide. |
| create_single_slideA | Generate a single AI-designed slide from a topic. Use for hero slides, social-media graphics, or one-off visuals. For a full multi-slide deck, use create_presentation_from_topic. Returns a job ID; poll check_job_status until status is completed. Faster than full-deck generation (typically 20-40 seconds). |
| create_presentation_from_contentA | Transform raw text (articles, notes, transcripts, reports, outlines) into a polished presentation. Use when the caller has prose or notes already and wants a deck built from that source material. Honor preservationMode: 'preserve' keeps the structure and auto-counts slides, 'enhance' rewrites for clarity, 'summarize' condenses, 'instruction' uses topic as a directive. For file uploads (PDF/DOCX/PPTX) use create_presentation_from_file. Returns a job ID; poll check_job_status. |
| create_presentation_from_fileA | Convert an uploaded document (PDF, Word, PowerPoint, plain text, markdown, RTF) into a presentation. Use when the caller already has a source document. Max 5 MB after base64 encoding. Supports the same preservation modes as create_presentation_from_content. For pasted raw text use create_presentation_from_content. Returns a job ID; poll check_job_status. |
| check_job_statusA | Poll for the result of an async presentation job. Use after any create_* call that returned a jobId. Safe to call repeatedly; does not consume job state. Recommended cadence: wait 55-60 seconds before the first poll, then every 30-35 seconds. Most jobs complete within 2 minutes. When status is 'completed', the response includes docurl (viewer link), docid (numeric ID), and optionally animated_url and thumbnailUrl. When status is 'failed', the response includes an error field. While 'processing', keep polling. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/slidecraft-in/presentations-ai-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server