This server lets you create AI-powered, professionally designed slide decks and individual slides from various inputs, then track their generation progress.
Create a full presentation from a topic — Provide a subject or brief and generate a complete deck (1–50 slides) with configurable tone, target audience, and language.
Create a single designed slide — Generate one hero slide or social-media-style graphic from a topic, without building a full deck.
Create a presentation from raw text — Transform articles, notes, transcripts, or outlines into a polished deck, with content handling modes: enhance, preserve, summarize, or instruction.
Create a presentation from a file — Upload a document (PDF, DOCX, PPTX, TXT, MD, or RTF, up to 5 MB) and convert it into a presentation using the same preservation modes.
Check job status — Poll async generation jobs to retrieve the viewer URL, document ID, thumbnails, or error details once complete.
Flexible export formats — Output as editable PowerPoint (PPTX), PDF, image thumbnails, HTML render, or a shareable viewer URL.
Customization & branding — All tools support optional tone, audience, language (ISO 639-1), and company domain for branding context.
Webhook support — Optionally provide a callback URL for automated job-completion notifications.
Official Model Context Protocol server for Presentations.AI. Create designed slide decks from a topic, text, or document via any MCP-compatible client.
https://api.presentations.ai/mcpProperty | Value |
Transport | Streamable HTTP |
Authentication | OAuth 2.0 with PKCE + Dynamic Client Registration |
Protocol version | 2025-06-18 |
A Presentations.AI account is required. The server opens a browser for sign-in on first connect; no API key handling on the client side.
Related MCP server: Alai
Tool | Purpose |
| Full deck from a topic / brief |
| A single designed slide on a topic (image) |
| Deck from raw text — article, notes, transcript |
| Deck from PDF, DOCX, PPTX, TXT, or MD (≤ 5 MB) |
| Poll long-running async jobs |
For exact parameter shapes and exports (pptx, pdf, image, share, render),
see the REST + MCP reference.
Claude Desktop / Claude.ai — docs/clients/claude-desktop.md
Cursor — docs/clients/cursor.md
Cline — docs/clients/cline.md
VS Code — docs/clients/vs-code.md
Gemini CLI — docs/clients/gemini-cli.md
presentations-ai-skills — Claude Code skill bundle
presentations-ai-gemini-extension — Gemini CLI extension
support@presentations.ai
MIT — see LICENSE.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes | The job ID returned from a create_* call when immediatePollUrl=true or when callback_url was omitted. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that it's safe to call repeatedly, does not consume job state. Details response fields for each status (completed, failed, processing). No annotations provided, so description carries full burden and does it well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Paragraph is well-structured and front-loaded with purpose. Each sentence adds value. Could be slightly more concise but is efficient overall.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one param, no output schema), the description covers purpose, usage, behavior, and response fields completely. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only parameter jobId has schema description 'The job ID returned from a create_* call when immediatePollUrl=true or when callback_url was omitted.' Schema coverage 100%, but description adds context about where jobId comes from, adding value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Poll for the result of an async presentation job' and specifies it's used after any create_* call that returned a jobId. This distinguishes it from sibling create tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use after any create_* call that returned a jobId' and provides recommended polling cadence (55-60s first, then 30-35s). No explicit when-not, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | Raw text content (markdown supported). The source material the deck is built from. | |
| exportType | Yes | Output format. See create_presentation_from_topic for options. | |
| preservationMode | No | How to handle the content. 'enhance'/'summarize'/'instruction' require slideCount; 'preserve' auto-determines slide count. Defaults to 'enhance'. | |
| slideCount | No | Number of slides. Omit when preservationMode is 'preserve' (auto). Required for all other modes. | |
| topic | No | Title override, or instruction text when preservationMode is 'instruction'. | |
| language | No | ISO 639-1 language code. Defaults to 'en'. | |
| domain | No | Company domain for branding context. | |
| target_audience | No | Audience profile. | |
| tone | No | Voice and register. | |
| callback_url | No | HTTPS webhook posted when the job finishes. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses that the tool returns a job ID and suggests polling check_job_status, but does not cover auth requirements or potential side effects. Still, the async nature is clearly communicated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single paragraph with front-loaded purpose, each sentence earns its place. No redundancy or verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers main purpose, usage, parameter behaviors, return value (job ID), and sibling distinction. Lacks examples for callback_url or further detail on output, but overall sufficient for an async creation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds significant extra context: details on preservationMode (which modes require slideCount), topic override vs instruction, and cross-reference to create_presentation_from_topic for exportType options.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool transforms raw text into a polished presentation, specifies the use case (caller has prose/notes), and distinguishes from sibling tools like create_presentation_from_file for file uploads.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use (when caller has prose/notes) and when not (for file uploads use create_presentation_from_file). Also explains preservationMode behaviors and dependencies.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| file_data | Yes | Base64-encoded file contents. Max 5 MB encoded size. | |
| file_name | Yes | Original filename including extension. | |
| mime_type | Yes | MIME type of the source document. Must match the file extension. | |
| exportType | Yes | Output format. See create_presentation_from_topic for options. | |
| preservationMode | No | How to handle the content. 'preserve' auto-counts slides; other modes need slideCount. | |
| slideCount | No | Number of slides. Required unless preservationMode is 'preserve'. | |
| topic | No | Title override, or instruction text when preservationMode is 'instruction'. | |
| language | No | ISO 639-1 language code. Defaults to 'en'. | |
| domain | No | Company domain for branding context. | |
| target_audience | No | Audience profile. | |
| tone | No | Voice and register. | |
| callback_url | No | HTTPS webhook posted when the job finishes. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description provides key behavioral details: max size 5 MB, supports preservation modes, returns a job ID, and requires polling. Lacks mention of any destructive side effects, but creation tools typically imply mutation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences cover all critical points: purpose, usage guidance, constraints, and follow-up steps. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 12 parameters (mostly optional) and no output schema, the description covers essential behavioral aspects: size limit, return type, polling, and references to sibling for options. Could mention error handling or example, but sufficient for an experienced agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. Description adds value beyond schema: size limit for file_data, match requirement for mime_type, references to sibling tool for preservationMode and exportType options, and notes on slideCount dependency.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Convert an uploaded document ... into a presentation,' listing supported file types. It distinguishes from sibling tool 'create_presentation_from_content' by noting the different input method.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: 'Use when the caller already has a source document.' Provides clear alternative: 'For pasted raw text use create_presentation_from_content.' Also mentions polling via check_job_status.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes | Topic, headline, or short brief that drives the deck. | |
| slideCount | Yes | Number of slides to generate (1-50). | |
| exportType | Yes | Output format. Use 'share' for a viewer URL, 'pptx' for editable PowerPoint, 'pdf' for read-only, 'image' for thumbnails, 'render' for HTML. | |
| language | No | ISO 639-1 language code (e.g. 'en', 'es'). Defaults to 'en'. | |
| domain | No | Company domain (e.g. 'acme.com') for branding context. | |
| target_audience | No | Audience profile that shapes vocabulary and depth. | |
| tone | No | Voice and register of the generated copy. | |
| callback_url | No | HTTPS webhook the API will POST to when the job finishes. Mutually exclusive with polling. | |
| immediatePollUrl | No | When true, returns a jobId immediately for polling via check_job_status. When false, blocks until generation completes. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the async behavior: returns a job ID, poll via check_job_status, then use docurl. It does not detail failure modes, authentication needs, or rate limits, but the core behavioral flow is well explained.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is four sentences, each adding essential information: what the tool does, when to use it, how the async flow works, and an alternative. No fluff, and critical details are front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex tool with 9 parameters, no annotations, no output schema, and sibling tools, the description provides a complete picture: usage context, async flow with polling, and alternative tool. It covers the key aspects an agent needs to invoke and manage the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides 100% coverage with descriptions for all 9 parameters. The description does not add additional meaning beyond the schema—it mentions topic, slideCount, etc., but that matches schema descriptions. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action: 'Generate a full AI-powered presentation from a topic or brief.' It specifies the resource (presentation) and scope (from topic/brief), and distinguishes from sibling tool create_single_slide by noting when to use the alternative.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit when-to-use: 'Use when the caller has a subject line, headline, or short brief and wants a complete deck.' It also provides an alternative: 'For a single hero slide instead of a deck, use create_single_slide.' Additionally, it explains the async processing flow and directs to check_job_status for polling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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).
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes | Subject of the slide. | |
| exportType | Yes | Output format. 'image' gives a PNG, 'pptx' an editable slide, 'share' a viewer URL. | |
| language | No | ISO 639-1 language code. Defaults to 'en'. | |
| domain | No | Company domain for branding context. | |
| target_audience | No | Audience profile. | |
| tone | No | Voice and register. | |
| callback_url | No | HTTPS webhook posted when the job finishes. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses async behavior (returns job ID, poll check_job_status), typical completion time (20-40 seconds), and faster-than-full-deck nature. No annotations provided, so description carries full burden and does well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with purpose, no redundant words. Every sentence adds value: purpose, use cases, sibling alternative, async mechanics, and speed comparison.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, usage, async behavior, polling instruction, timing, and sibling distinction. Without output schema, description appropriately explains what to expect (job ID) and how to use it. Complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents parameters thoroughly. Description adds context about return value (job ID) but does not add new parameter-specific semantics beyond schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb 'Generate' and specific resource 'a single AI-designed slide from a topic'. Lists use cases (hero slides, social-media graphics, one-off visuals) and distinguishes from sibling tool create_presentation_from_topic for multi-slide decks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use (hero slides, social-media graphics, one-off visuals) and when not (full multi-slide deck, directing to create_presentation_from_topic). Clear guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each creation tool has a distinct input type (raw text, file, topic, single slide) with explicit cross-references in descriptions, making selection unambiguous. The polling tool is clearly separate and serves all creation tools.
All tool names follow a consistent verb_noun pattern using snake_case (check_job_status, create_presentation_from_content, etc.), with verbs 'check' and 'create' and nouns describing the input or target.
Five tools cover all essential creation pathways (content, file, topic, single slide) plus async polling, which is well-scoped for a presentation generation server without unnecessary bloat.
The set provides complete coverage for generating presentations from various sources and checking results. No obvious gaps exist for its stated purpose of AI-powered presentation creation.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Generate, edit, and export AI presentations to PDF, PPTX, or a shareable link.
Generate polished PowerPoint presentations from text prompts, YouTube videos, or structured outlin…
Generate professional PowerPoint presentations from text, YouTube videos, or structured JSON data.…
AI presentation and report generation: slides, diagrams, PPTX export, live preview MCP App.
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
