Filetopdf MCP vs Slideshot — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Filetopdf MCP vs Slideshot
In-depth architectural comparison of the Filetopdf MCP and Slideshot MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Filetopdf MCP
Multimedia Process · Local stdio
Quality: 57/100 (Good) | Auth: API Key required
Slideshot
Multimedia Process · Local stdio
Quality: 64/100 (Good) | Auth: No auth required
Verdict Summary: Choose Filetopdf MCP if you need specialized Multimedia Process tools running via a local process. Choose Slideshot if your workspace requires Multimedia Process integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Filetopdf MCP when:
You need dedicated capabilities in the Multimedia Process domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Freemium).
You have access to required keys: FILETOPDF_API_KEY.
Convert files (DOCX, XLSX, PPTX, images…), HTML, and Markdown to pixel-perfect PDFs via the FileToPDF API. Returns the PDF as an embedded resource or saves it to disk. Runs via npx filetopdf-mcp or a hosted Streamable HTTP endpoint; free API key in one click.
Convert HTML to PDF/PNG/WebP/PPTX slide carousels with 11 themes (LinkedIn, Instagram, pitch decks, infographics). Pixel-perfect Puppeteer rendering, dimension-aware reflow for portrait/landscape, token-efficient JSON mode. npx slideshot-mcp.
Category & Scope
Tools & Capabilities Breakdown
Filetopdf MCP Tools (4)
get_account
Check the FileToPDF connection and return the plan, remaining conversion credits, and subscription status. Free — never costs credits. Call it to verify the API key works, or after a failed conversion to see whether credits ran out. No API key yet? Anyone can get one free, in one click, at https://filetopdf.dev (10 free conversions, no signup).
convert_file
Convert a document at a public URL into a PDF. Handles Office documents (DOCX, XLSX, PPTX, ODT, RTF, TXT, CSV…), images (PNG, JPG, WebP…), web pages/HTML files, Markdown files, and existing PDFs (passthrough) — the conversion engine is auto-detected from the file extension. Use this when the source lives at a URL; for raw HTML or Markdown strings use convert_html / convert_markdown instead. Returns the PDF as an embedded application/pdf resource (optionally also written to disk via save_path). Costs 1 credit on success; failed conversions are free.
convert_html
Render a raw HTML string into a pixel-perfect PDF with a real Chromium engine — ideal for generating invoices, reports, receipts, certificates, letters, and other documents from templates. Optional css is injected into the document <head>; full layout control via paper size, margins, landscape, scale, page ranges, background printing, PDF/A archival conformance, and password protection. Returns the PDF as an embedded application/pdf resource (optionally also written to disk via save_path). Costs 1 credit on success; failed conversions are free.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Filetopdf MCP is categorized under Multimedia Process and uses a local stdio subprocess. In contrast, Slideshot belongs to Multimedia Process using local stdio subprocess. Select Filetopdf MCP when you need capabilities focused on multimedia process and Slideshot when you require tools for multimedia process.
Render a Markdown string into a clean, professional PDF — the fastest way to turn notes, reports, documentation, summaries, or any agent-written text into a shareable document. A sensible default stylesheet is applied when no css is given; pass custom CSS to fully control typography and branding, plus layout options (paper size, margins, landscape, page ranges, PDF/A, passwords). Returns the PDF as an embedded application/pdf resource (optionally also written to disk via save_path). Costs 1 credit on success; failed conversions are free.
Slideshot Tools (6)
discover_themes
MANDATORY first step — all other tools REJECT until this is called. Returns themes, orientation presets, token-usage modes, and output formats. Use ONLY the native selector prompts from the "ask" array — DO NOT render themes as a separate markdown list. DO NOT ask how many slides (you decide based on topic). After user picks options, show a data outline of proposed slides and WAIT for confirmation before calling create_slides.
create_slides
Create slides. IMPORTANT: Use mode=default unless the user explicitly chose token_saver. mode=default = AI writes full HTML (best quality). mode=token_saver = AI sends JSON, server uses basic templates. REQUIRES discover_themes first AND user must have confirmed the data outline. After this tool saves the HTML, you MUST show the htmlPath as a code preview artifact. Then STOP and ask the user to confirm. DO NOT call render_slides until the user explicitly confirms.
render_slides
Final render to PDF/WebP/PNG/PPTX. Accepts html string OR htmlPath. Supports width, height, selector, scale, webpQuality, orientation, pptxMode, pptxFilename, slideRange. NEVER call render_slides in the same turn as create_slides. When the user provides an existing HTML file path, pass it as htmlPath and call this tool directly — no discover_themes or create_slides needed. For the full slide-creation workflow, REQUIRES both discover_themes AND create_slides first, and ONLY call AFTER user confirms the preview. Returns file paths on disk.
list_themes
Idempotent read-only listing of all available themes (8+). Unlike discover_themes, this does NOT start a slide-creation workflow — call it any time the user asks "what themes are there?" mid-conversation. Returns the same tiered theme catalog (primary/secondary). Models MUST present every theme returned, never truncate.
edit_slides
Token-efficient partial edits on a previously-generated HTML deck. Use this INSTEAD of regenerating the whole deck for small changes — it saves 60-90% tokens vs a full rewrite. Operations: replace_slide (swap one slide block by 1-indexed slideIndex), patch_css (append CSS rules to <style>), swap_token (replace a CSS variable's value, e.g. {"--coral": "#FF0000"}), patch_class (add/remove a class on a specific slide, e.g. {"add": "dark"}). Reads from cache or htmlPath; saves the updated HTML and returns the new htmlPath. After editing, show the htmlPath as a preview artifact and STOP — do NOT call render_slides until the user confirms.
health_check
Verify Puppeteer/Chromium can launch. Use when render fails.