Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

SlideMaster

NPM · @SLIDEMASTER/MCP-SERVER · SCANNED SEP 20

Create AI presentation videos with slides, narration, TTS audio, and MP4 export from any topic.

0 this week 80 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability87
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 2196 tokens (~81/item across 27 items; 27 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 28 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the SlideMaster MCP server?

SlideMaster runs locally as an npm package, launched with npx -y @slidemaster/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @slidemaster/mcp-server

# add to Claude Code
claude mcp add headdao-slidemaster-mcp -- npx -y @slidemaster/mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "headdao-slidemaster-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@slidemaster/mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "headdao-slidemaster-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@slidemaster/mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add headdao-slidemaster-mcp -- npx -y @slidemaster/mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "headdao-slidemaster-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@slidemaster/mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add headdao-slidemaster-mcp --command npx --arg -y --arg @slidemaster/mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  headdao-slidemaster-mcp:
    command: "npx"
    args: ["-y", "@slidemaster/mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "headdao-slidemaster-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@slidemaster/mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add headdao-slidemaster-mcp -t stdio -c npx -a -y @slidemaster/mcp-server
// mcp.json
{
  "mcpServers": {
    "headdao-slidemaster-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@slidemaster/mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.83 functional
  • 15 Sept 26 +1
    • Stability: 0.97 → pass security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 8 Sept 26 +1
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/@slidemaster/mcp-server@1.6.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 95 packages
Packages resolved 95
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 27 exposed · ~2,036 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
analyze_style_image ~72

Upload a style reference image to analyze its visual style (colors, fonts, layout). Returns a style_guide object that can be passed to render_slides to apply this style to all slides.

NameTypeReqDescription
image_urlstringyesPublic URL of the style reference image (PNG, JPG, or any image URL)

No output schema declared.

No examples provided.

batch_generate_scripts ~93

Use this to generate narration scripts for all slides in a project in one batch.

NameTypeReqDescription
project_idstringyesProject ID to generate scripts for
prompt_stylestring'professional' | 'casual' | 'educational'
regeneratebooleanForce regeneration if scripts exist (default: false)
slide_idsarrayOptional subset of slide IDs; omit for all slides

No output schema declared.

No examples provided.

check_status ~39

Use this to poll processing progress after triggering render, TTS, or video generation.

NameTypeReqDescription
project_idstringyesProject ID to check status for

No output schema declared.

No examples provided.

create_project ~80

Use this to create a new empty project. Returns the project_id needed for all subsequent operations.

NameTypeReqDescription
descriptionstringOptional project description
titlestringyesProject title, e.g. 'Q3 Sales Report'
typestring'traditional' (slides) or 'flow' (screen recording). Default: 'traditional'

No output schema declared.

No examples provided.

delete_project ~44

Use this to permanently delete a project and all its slides, audio, and video. Do not use for archiving.

NameTypeReqDescription
project_idstringyesProject ID to delete

No output schema declared.

No examples provided.

delete_slide ~32

Use this to permanently remove a single slide from a project.

NameTypeReqDescription
slide_idstringyesSlide ID to delete

No output schema declared.

No examples provided.

evercam_status ~48

Poll EverCam export progress. Returns status (processing/completed/failed/not_started) and download_url when completed.

NameTypeReqDescription
project_idstringyesProject ID to check EverCam export status

No output schema declared.

No examples provided.

export_evercam ~58

Export project as an EverCam offline HTML5 playable package (ZIP). Requires video to be generated first. This is async — call evercam_status to poll progress.

NameTypeReqDescription
project_idstringyesProject ID to export as EverCam

No output schema declared.

No examples provided.

export_pdf ~50

Export all rendered slides as a single PDF file. Returns a download URL for the PDF (16:9 landscape, one slide per page).

NameTypeReqDescription
project_idstringyesProject ID to export as PDF

No output schema declared.

No examples provided.

export_pptx ~45

Export all rendered slides as a single PPTX (PowerPoint) file. Returns a download URL.

NameTypeReqDescription
project_idstringyesProject ID to export as PPTX

No output schema declared.

No examples provided.

export_project ~39

Use this to get download URLs for all generated assets: slides, audio, and video files.

NameTypeReqDescription
project_idstringyesProject ID to export

No output schema declared.

No examples provided.

generate_outline ~133

Use this when the user wants to plan a presentation. Generates slide titles and descriptions from a topic. Automatically creates a project and returns project_id — no need to call create_project separately.

NameTypeReqDescription
languagestring'zh-TW' | 'zh-CN' | 'en' | 'ja' (default: 'zh-TW')
slides_countintegerNumber of slides (default: 8)
stylestring'professional' | 'playful' | 'minimalist'
topicstringyesThe topic or prompt, e.g. 'Introduction to Machine Learning'

No output schema declared.

No examples provided.

generate_script ~79

Use this to generate a narration script for a single slide using AI.

NameTypeReqDescription
prompt_stylestring'professional' | 'casual' | 'educational' (default: 'professional')
regeneratebooleanForce regeneration if script exists (default: false)
slide_idstringyesSlide ID to generate a script for

No output schema declared.

No examples provided.

generate_tts ~140

Use this to generate text-to-speech audio. Pass project_id for all slides or slide_id for one slide.

NameTypeReqDescription
project_idstringProject ID — generates TTS for all slides
slide_idstringSlide ID — generates TTS for one slide
speaking_ratenumberSpeed multiplier, e.g. 0.8 slower, 1.2 faster (default: 1.0)
tts_providerstring'gemini' | 'cosyvoice' | 'azure'
voice_namestringVoice ID from the provider. Use list_voices to browse.

No output schema declared.

No examples provided.

generate_video ~108

Use this as the final step to compile slides + audio into an MP4 video. Poll check_status afterward.

NameTypeReqDescription
forcebooleanForce regeneration if video exists (default: false)
fpsintegerFrames per second (default: 30)
project_idstringyesProject ID to generate video for
resolutionarray[width, height], e.g. [1920, 1080] (default: [1920, 1080])

No output schema declared.

No examples provided.

get_credit_balance ~62

Check remaining API credits before starting expensive operations. Call this before large projects (>10 slides) to avoid mid-job failures. 1 complete 25-slide course costs ~3,980 credits (render 3,500 + TTS 400 + video 80).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_project ~33

Use this to retrieve detailed metadata and status for a specific project.

NameTypeReqDescription
project_idstringyesProject ID to retrieve

No output schema declared.

No examples provided.

get_project_context ~66

Get a complete snapshot of a project in one call: metadata, all slides with script/audio status, progress summary, and what to do next. Call this after any long-running operation to orient yourself before deciding the next action.

NameTypeReqDescription
project_idstringyesProject ID to inspect

No output schema declared.

No examples provided.

list_projects ~48

Use this when the user wants to see their existing projects. Returns a paginated project list.

NameTypeReqDescription
limitintegerMax results to return (default: 50, max: 100)

No output schema declared.

No examples provided.

list_slides ~42

Use this to list all slides in a project with their titles, scripts, and render status.

NameTypeReqDescription
project_idstringyesProject ID to list slides for

No output schema declared.

No examples provided.

list_voices ~54

Use this to browse available TTS voices across all providers before generating audio.

NameTypeReqDescription
providerstringFilter by provider: 'gemini' | 'cosyvoice' | 'azure'. Omit for all providers.

No output schema declared.

No examples provided.

render_slides ~135

Use this to generate AI slide images for a project. Each slide gets a background image from the AI model. Optionally pass a style_guide (from analyze_style_image) to apply a consistent visual style.

NameTypeReqDescription
image_sizestringResolution: '1K' | '2K' | '4K' (default: '2K')
project_idstringyesTarget project ID
slidesarrayyesArray of {title, description} objects
style_guideobjectStyle guide object from analyze_style_image. Pass this to apply a consistent visual style to all slides.

No output schema declared.

No examples provided.

topic_to_video ~238

Use this for one-click presentation creation from a topic. Default: slides only. Set include_scripts=true for narration, include_video=true for full MP4. Poll check_status afterward.

NameTypeReqDescription
image_sizestringResolution: '1K' | '2K' | '4K' (default: '2K')
include_scriptsbooleanGenerate narration scripts (default: false)
include_videobooleanGenerate TTS + compile MP4, implies include_scripts (default: false)
languagestring'zh-TW' | 'zh-CN' | 'en' | 'ja' (default: 'zh-TW')
slides_countintegerNumber of slides (default: 8)
stylestring'professional' | 'playful' | 'minimalist'
topicstringyesThe topic, e.g. 'Introduction to Machine Learning'
tts_providerstring'gemini' | 'cosyvoice' | 'azure'
tts_voicestringVoice name/ID from the chosen provider

No output schema declared.

No examples provided.

update_project ~138

Use this to update project settings like title, description, TTS provider, voice, or language.

NameTypeReqDescription
descriptionstringNew project description
project_idstringyesProject ID to update
titlestringNew project title
tts_languagestringLanguage code, e.g. 'zh-TW', 'en'
tts_providerstring'gemini' | 'cosyvoice' | 'azure'
tts_speaking_ratenumberSpeed multiplier (default: 1.0)
tts_voicestringVoice name/ID

No output schema declared.

No examples provided.

update_slide ~54

Use this to edit a slide's title or narration script text.

NameTypeReqDescription
scriptstringNew narration script text
slide_idstringyesSlide ID to update
titlestringNew slide title

No output schema declared.

No examples provided.

upload_complete ~43

Use this after the file has been uploaded to the pre-signed URL. Triggers server-side processing.

NameTypeReqDescription
project_idstringyesProject ID returned from upload_init

No output schema declared.

No examples provided.

upload_init ~63

Use this to upload an existing PPTX or PDF file. Returns a pre-signed upload URL and project_id.

NameTypeReqDescription
filenamestringyesOriginal filename with extension, e.g. 'deck.pptx'
titlestringyesTitle for the uploaded presentation

No output schema declared.

No examples provided.

Common questions

What is the SlideMaster MCP server?

SlideMaster is an MCP server listed in the public MCP registry as io.github.Headdao/slidemaster-mcp. Create AI presentation videos with slides, narration, TTS audio, and MP4 export from any topic. This page covers its npm package (@slidemaster/mcp-server).

Is the SlideMaster MCP server safe to use?

SlideMaster scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the SlideMaster MCP server expose?

SlideMaster exposes 27 tools: generate_outline, create_project, upload_init, upload_complete, analyze_style_image, and 22 more. Their descriptions and schemas cost roughly 2,036 tokens of context every time the server is loaded.

Is the SlideMaster MCP server still maintained?

SlideMaster is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the SlideMaster MCP server under?

SlideMaster declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.