Apify Document & Media Tools MCP server
Commit Nov 7, 2026Enables AI agents to convert documents to Markdown, perform OCR, transcribe audio, generate speech, take website screenshots, and extract video frames.
Also known as AndriyVK/-apify-document-tools, apify-document-tools
- Stars
- 0
- Tools
- 14
- Downloads, 30 days
- —
- Latest version
- 0.4.0
- Last commit
- Nov 7, 2026
- License
- MIT
What is Apify Document & Media Tools MCP?
Apify Document & Media Tools enables AI agents to convert documents to Markdown, perform OCR, transcribe audio, generate speech, take website screenshots, and extract video frames. It exposes 14 tools, such as get-actor-run, get-dataset-items, get-key-value-store-record.
Summary generated from the project's README
About Apify Document & Media Tools MCP server
Converting complex documents and media files into machine-readable formats is what this server enables for AI agents. Developers using Claude, Cursor, or ChatGPT can provide public file URLs to perform tasks like transcribing audio with Whisper large-v3, converting office documents to PDF, or extracting text from images via OCR in 38 languages. The server also handles website screenshots, video frame extraction, and domain DNS or SSL checks.
Users can set up the server locally using a Python installation and an Apify API token, or connect via a hosted URL. To prevent unexpected costs, every tool includes a max_charge_usd safety limit, which defaults to one dollar per call. The service is billed through Apify, with specific rates for different operations, such as one dollar per one thousand text pages for markdown conversion or five dollars per one thousand minutes for audio transcription.
What you can do with it
- 1Convert documents to MarkdownTransform PDFs, images, or Office files into Markdown or JSON tables for RAG applications.
- 2Transcribe audio and videoTurn audio files into timestamped text segments or SRT subtitles using Whisper.
- 3Capture website screenshotsTake full-page or element-specific screenshots of web pages for desktop or mobile views.
- 4Extract video framesPull specific frames from a video file based on timecodes or scene changes.
Written from the project's README. Every use case is checked against a quote from it.
How to install Apify Document & Media Tools MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Apify Document & Media Tools MCP in Claude Code
$ claude mcp add --transport http apify-document-tools 'https://mcp.apify.com/?tools=ai_admin/document-to-markdown,ai_admin/office-to-pdf,ai_admin/pdf-image-converter,ai_admin/audio-transcriber,ai_admin/image-to-text-ocr,ai_admin/text-to-speech,ai_admin/website-screenshot,ai_admin/domain-whois-dns-ssl,ai_admin/video-frame-extractor,ai_admin/social-video-transcript'Install Apify Document & Media Tools MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"apify-document-tools": {
"url": "https://mcp.apify.com/?tools=ai_admin/document-to-markdown,ai_admin/office-to-pdf,ai_admin/pdf-image-converter,ai_admin/audio-transcriber,ai_admin/image-to-text-ocr,ai_admin/text-to-speech,ai_admin/website-screenshot,ai_admin/domain-whois-dns-ssl,ai_admin/video-frame-extractor,ai_admin/social-video-transcript"
}
}
}Install Apify Document & Media Tools MCP in VS Code
.vscode/mcp.json
{
"servers": {
"apify-document-tools": {
"type": "http",
"url": "https://mcp.apify.com/?tools=ai_admin/document-to-markdown,ai_admin/office-to-pdf,ai_admin/pdf-image-converter,ai_admin/audio-transcriber,ai_admin/image-to-text-ocr,ai_admin/text-to-speech,ai_admin/website-screenshot,ai_admin/domain-whois-dns-ssl,ai_admin/video-frame-extractor,ai_admin/social-video-transcript"
}
}
}Install Apify Document & Media Tools MCP in VS Code CLI
$ code --add-mcp '{"name":"apify-document-tools","type":"http","url":"https://mcp.apify.com/?tools=ai_admin/document-to-markdown,ai_admin/office-to-pdf,ai_admin/pdf-image-converter,ai_admin/audio-transcriber,ai_admin/image-to-text-ocr,ai_admin/text-to-speech,ai_admin/website-screenshot,ai_admin/domain-whois-dns-ssl,ai_admin/video-frame-extractor,ai_admin/social-video-transcript"}'Install Apify Document & Media Tools MCP in Codex
$ codex mcp add apify-document-tools --url 'https://mcp.apify.com/?tools=ai_admin/document-to-markdown,ai_admin/office-to-pdf,ai_admin/pdf-image-converter,ai_admin/audio-transcriber,ai_admin/image-to-text-ocr,ai_admin/text-to-speech,ai_admin/website-screenshot,ai_admin/domain-whois-dns-ssl,ai_admin/video-frame-extractor,ai_admin/social-video-transcript'Install Apify Document & Media Tools MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.apify-document-tools] url = "https://mcp.apify.com/?tools=ai_admin/document-to-markdown,ai_admin/office-to-pdf,ai_admin/pdf-image-converter,ai_admin/audio-transcriber,ai_admin/image-to-text-ocr,ai_admin/text-to-speech,ai_admin/website-screenshot,ai_admin/domain-whois-dns-ssl,ai_admin/video-frame-extractor,ai_admin/social-video-transcript"
Install Apify Document & Media Tools MCP in Gemini CLI
$ gemini mcp add -s user --transport http apify-document-tools 'https://mcp.apify.com/?tools=ai_admin/document-to-markdown,ai_admin/office-to-pdf,ai_admin/pdf-image-converter,ai_admin/audio-transcriber,ai_admin/image-to-text-ocr,ai_admin/text-to-speech,ai_admin/website-screenshot,ai_admin/domain-whois-dns-ssl,ai_admin/video-frame-extractor,ai_admin/social-video-transcript'Install Apify Document & Media Tools MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"apify-document-tools": {
"url": "https://mcp.apify.com/?tools=ai_admin/document-to-markdown,ai_admin/office-to-pdf,ai_admin/pdf-image-converter,ai_admin/audio-transcriber,ai_admin/image-to-text-ocr,ai_admin/text-to-speech,ai_admin/website-screenshot,ai_admin/domain-whois-dns-ssl,ai_admin/video-frame-extractor,ai_admin/social-video-transcript",
"type": "http"
}
}
}Apify Document & Media Tools MCP tools 14
Read from the server with tools/listget-actor-runRead-onlyGet detailed information about a specific Actor run. Returns run result: status, storages (datasets/keyValueStores alias map), stats, summary, nextStep. - summary describes the past (e.g. "SUCCEEDED in 22s. 47 items; 3 fields available."). - nextStep prescribes one primary follow-up action with identifiers interpolated (e.g. "Use get-dataset-items with datasetId=..."). - waitSecs (0–45, default 30) waits up to that many seconds for terminal status before returning. USAGE: - Use to check the status of a run started by any Actor-running tool. - Pass waitSecs > 0 to block until terminal (or until the cap elapses). USAGE EXAMPLES: - user_input: Show details of run y2h7sK3Wc - user_input: Wait for run y2h7sK3Wc to finish
get-dataset-itemsRead-onlyGet items (rows) from a dataset — the output/results produced by an Actor run. Returns the rows themselves, not dataset metadata, counts, or a schema. When the user provides a datasetId and asks to retrieve results, output, data, or rows, call this tool directly. Default limit is 20. Use clean=true to skip empty items and hidden fields. USAGE: - Use when you need to read data from a dataset (all items or only selected fields). USAGE EXAMPLES: - user_input: Retrieve results from dataset abc123 - user_input: Get only metadata.url and title from dataset username~my-dataset
get-key-value-store-recordRead-onlyGet the value stored under a specific key in a key-value store — a single record, not a listing of all keys. Requires the exact key name. The response preserves the original Content-Encoding; most clients handle decompression automatically. A record over 262144 bytes is returned as a link to download it, not as its value. USAGE: - Use when you need to retrieve a specific record (JSON, text, or binary) from a store. USAGE EXAMPLES: - user_input: Get record INPUT from store abc123 - user_input: Get record data.json from store username~my-store
abort-actor-runActionAbort an Actor run that is currently starting or running. For runs with status SUCCEEDED, FAILED, ABORTING, ABORTED, or TIMED-OUT, this call has no effect. The results will include the updated run details after the abort request. USAGE: - Use when you need to stop a run that is taking too long or misconfigured. USAGE EXAMPLES: - user_input: Abort run y2h7sK3Wc - user_input: Gracefully abort run y2h7sK3Wc
ai_admin--document-to-markdownActionThis tool calls the Actor "ai_admin/document-to-markdown" and retrieves its output results. Actor description: From $1 per 1,000 pages: PDF, scanned PDF and images (OCR incl. Ukrainian and Russian), DOCX, DOC, XLSX, XLS, PPTX, PPT, ODT, RTF and HTML to clean Markdown with headings and tables, plus JSON tables and RAG chunks. OCR charged only for scanned pages.
ai_admin--office-to-pdfActionThis tool calls the Actor "ai_admin/office-to-pdf" and retrieves its output results. Actor description: Convert Word, Excel, PowerPoint (incl. legacy DOC, XLS, PPT), OpenDocument, RTF, CSV, HTML and images to PDF or archival PDF/A-2b for courts, tax portals and archives. $10 per 1,000 documents, batch and merge, files stay inside the Actor.
ai_admin--pdf-image-converterActionThis tool calls the Actor "ai_admin/pdf-image-converter" and retrieves its output results. Actor description: $2 per 1,000 pages: PDF pages to PNG, JPG, WebP or TIFF (DPI, page ranges), images to PDF, and iPhone HEIC to JPG - both directions in one Actor. Resize, merge images into one PDF, download links and a ZIP of all files.
ai_admin--audio-transcriberActionThis tool calls the Actor "ai_admin/audio-transcriber" and retrieves its output results. Actor description: Whisper large-v3 for $5 per 1,000 minutes (30¢ an hour): transcribe MP3, WAV, M4A, MP4, MOV, WebM and more to text, timestamped segments and SRT/VTT subtitles. 99 languages incl. Ukrainian, no API key, hours-long files split automatically.
ai_admin--image-to-text-ocrActionThis tool calls the Actor "ai_admin/image-to-text-ocr" and retrieves its output results. Actor description: Extract text from images (PNG, JPG, WebP, TIFF, HEIC) and scanned PDF pages in bulk. Returns plain text plus lines and words with confidence and bounding boxes. 38 languages incl. Ukrainian, Chinese, Arabic. Auto-rotate.
ai_admin--text-to-speechActionThis tool calls the Actor "ai_admin/text-to-speech" and retrieves its output results. Actor description: Natural neural voices licensed for commercial use: text, PDF and Word files to MP3/WAV/OGG with SRT/VTT subtitles. 37 voices in 23 languages incl. 3 Ukrainian voices (rare on the market), English, German, Spanish. No API key, no per-character fees.
ai_admin--website-screenshotActionThis tool calls the Actor "ai_admin/website-screenshot" and retrieves its output results. Actor description: Capture full-page or viewport screenshots of websites (PNG, JPEG, WebP) and save web pages or raw HTML as PDF. Desktop, laptop, tablet and phone devices, dark mode, element screenshots, cookie banners hidden, lazy images loaded.
ai_admin--domain-whois-dns-sslActionThis tool calls the Actor "ai_admin/domain-whois-dns-ssl" and retrieves its output results. Actor description: Check many domains at once: registration (RDAP/WHOIS) with registrar, creation and expiry dates, availability; DNS records A, AAAA, MX, NS, TXT, SPF, DMARC, CAA; SSL certificate issuer, validity and days left. For monitoring, SEO and lead research.
| get-actor-run | Get detailed information about a specific Actor run. Returns run result: status, storages (datasets/keyValueStores alias map), stats, summary, nextStep. - summary describes the past (e.g. "SUCCEEDED in 22s. 47 items; 3 fields available."). - nextStep prescribes one primary follow-up action with identifiers interpolated (e.g. "Use get-dataset-items with datasetId=..."). - waitSecs (0–45, default 30) waits up to that many seconds for terminal status before returning. USAGE: - Use to check the status of a run started by any Actor-running tool. - Pass waitSecs > 0 to block until terminal (or until the cap elapses). USAGE EXAMPLES: - user_input: Show details of run y2h7sK3Wc - user_input: Wait for run y2h7sK3Wc to finish | Read-only |
| get-dataset-items | Get items (rows) from a dataset — the output/results produced by an Actor run. Returns the rows themselves, not dataset metadata, counts, or a schema. When the user provides a datasetId and asks to retrieve results, output, data, or rows, call this tool directly. Default limit is 20. Use clean=true to skip empty items and hidden fields. USAGE: - Use when you need to read data from a dataset (all items or only selected fields). USAGE EXAMPLES: - user_input: Retrieve results from dataset abc123 - user_input: Get only metadata.url and title from dataset username~my-dataset | Read-only |
| get-key-value-store-record | Get the value stored under a specific key in a key-value store — a single record, not a listing of all keys. Requires the exact key name. The response preserves the original Content-Encoding; most clients handle decompression automatically. A record over 262144 bytes is returned as a link to download it, not as its value. USAGE: - Use when you need to retrieve a specific record (JSON, text, or binary) from a store. USAGE EXAMPLES: - user_input: Get record INPUT from store abc123 - user_input: Get record data.json from store username~my-store | Read-only |
| abort-actor-run | Abort an Actor run that is currently starting or running. For runs with status SUCCEEDED, FAILED, ABORTING, ABORTED, or TIMED-OUT, this call has no effect. The results will include the updated run details after the abort request. USAGE: - Use when you need to stop a run that is taking too long or misconfigured. USAGE EXAMPLES: - user_input: Abort run y2h7sK3Wc - user_input: Gracefully abort run y2h7sK3Wc | Action |
| ai_admin--document-to-markdown | This tool calls the Actor "ai_admin/document-to-markdown" and retrieves its output results. Actor description: From $1 per 1,000 pages: PDF, scanned PDF and images (OCR incl. Ukrainian and Russian), DOCX, DOC, XLSX, XLS, PPTX, PPT, ODT, RTF and HTML to clean Markdown with headings and tables, plus JSON tables and RAG chunks. OCR charged only for scanned pages. | Action |
| ai_admin--office-to-pdf | This tool calls the Actor "ai_admin/office-to-pdf" and retrieves its output results. Actor description: Convert Word, Excel, PowerPoint (incl. legacy DOC, XLS, PPT), OpenDocument, RTF, CSV, HTML and images to PDF or archival PDF/A-2b for courts, tax portals and archives. $10 per 1,000 documents, batch and merge, files stay inside the Actor. | Action |
| ai_admin--pdf-image-converter | This tool calls the Actor "ai_admin/pdf-image-converter" and retrieves its output results. Actor description: $2 per 1,000 pages: PDF pages to PNG, JPG, WebP or TIFF (DPI, page ranges), images to PDF, and iPhone HEIC to JPG - both directions in one Actor. Resize, merge images into one PDF, download links and a ZIP of all files. | Action |
| ai_admin--audio-transcriber | This tool calls the Actor "ai_admin/audio-transcriber" and retrieves its output results. Actor description: Whisper large-v3 for $5 per 1,000 minutes (30¢ an hour): transcribe MP3, WAV, M4A, MP4, MOV, WebM and more to text, timestamped segments and SRT/VTT subtitles. 99 languages incl. Ukrainian, no API key, hours-long files split automatically. | Action |
| ai_admin--image-to-text-ocr | This tool calls the Actor "ai_admin/image-to-text-ocr" and retrieves its output results. Actor description: Extract text from images (PNG, JPG, WebP, TIFF, HEIC) and scanned PDF pages in bulk. Returns plain text plus lines and words with confidence and bounding boxes. 38 languages incl. Ukrainian, Chinese, Arabic. Auto-rotate. | Action |
| ai_admin--text-to-speech | This tool calls the Actor "ai_admin/text-to-speech" and retrieves its output results. Actor description: Natural neural voices licensed for commercial use: text, PDF and Word files to MP3/WAV/OGG with SRT/VTT subtitles. 37 voices in 23 languages incl. 3 Ukrainian voices (rare on the market), English, German, Spanish. No API key, no per-character fees. | Action |
| ai_admin--website-screenshot | This tool calls the Actor "ai_admin/website-screenshot" and retrieves its output results. Actor description: Capture full-page or viewport screenshots of websites (PNG, JPEG, WebP) and save web pages or raw HTML as PDF. Desktop, laptop, tablet and phone devices, dark mode, element screenshots, cookie banners hidden, lazy images loaded. | Action |
| ai_admin--domain-whois-dns-ssl | This tool calls the Actor "ai_admin/domain-whois-dns-ssl" and retrieves its output results. Actor description: Check many domains at once: registration (RDAP/WHOIS) with registrar, creation and expiry dates, availability; DNS records A, AAAA, MX, NS, TXT, SPF, DMARC, CAA; SSL certificate issuer, validity and days left. For monitoring, SEO and lead research. | Action |
Show all 14 toolsShow fewer tools
ai_admin--video-frame-extractorActionThis tool calls the Actor "ai_admin/video-frame-extractor" and retrieves its output results. Actor description: Extract still frames from video files (MP4, MOV, WebM, MKV, AVI): N evenly spaced, every N seconds, exact timestamps, scene changes or keyframes. JPG/PNG/WebP with timecodes, video metadata and a free contact sheet. Ready for AI vision.
ai_admin--social-video-transcriptActionThis tool calls the Actor "ai_admin/social-video-transcript" and retrieves its output results. Actor description: Transcripts and SRT/VTT subtitles of YouTube, TikTok, Instagram Reels, Facebook and X videos, translated into Ukrainian and 20 other languages in the same run. Captions first, Whisper large-v3 when there are none. Failed videos are free. No API key.
| ai_admin--video-frame-extractor | This tool calls the Actor "ai_admin/video-frame-extractor" and retrieves its output results. Actor description: Extract still frames from video files (MP4, MOV, WebM, MKV, AVI): N evenly spaced, every N seconds, exact timestamps, scene changes or keyframes. JPG/PNG/WebP with timecodes, video metadata and a free contact sheet. Ready for AI vision. | Action |
| ai_admin--social-video-transcript | This tool calls the Actor "ai_admin/social-video-transcript" and retrieves its output results. Actor description: Transcripts and SRT/VTT subtitles of YouTube, TikTok, Instagram Reels, Facebook and X videos, translated into Ukrainian and 20 other languages in the same run. Captions first, Whisper large-v3 when there are none. Failed videos are free. No API key. | Action |
Configuration
APIFY_TOKEN
| Name | Description | |
|---|---|---|
| APIFY_TOKEN | — |
Automated checks
Ran Nov 16, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableandriyvk/-apify-document-tools is public and reachablegithub.com/andriyvk/-apify-document-tools ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-16github.com/andriyvk/-apify-document-tools ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model14 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-11-25 in 3969 ms; tools/list returned 14 tools (HostedMCP test account)Pass
README
View on GitHubMCP server: document & media tools for AI agents
Tools for Claude, Cursor, ChatGPT and any other MCP client, backed by open-source Actors on Apify:
| Tool | What it does | Price (billed by Apify) |
|---|---|---|
convert_document_to_markdown |
PDF (text and scanned, OCR in 11 languages), images, DOCX/DOC, XLSX/XLS, PPTX/PPT, ODT, RTF, HTML → Markdown, JSON tables, RAG chunks | $1 / 1,000 text pages, $4 / 1,000 OCR pages |
convert_office_to_pdf |
Word, Excel, PowerPoint, OpenDocument, RTF, HTML, images → PDF or PDF/A-2b, optional merge | $10 / 1,000 documents |
convert_pdf_or_images |
PDF pages → PNG/JPG/WebP/TIFF, images ↔ PDF, iPhone HEIC → JPG, resize | $2 / 1,000 images |
transcribe_audio |
Audio and video → text, timestamped segments, SRT/VTT (Whisper large-v3, 99 languages) | $5 / 1,000 minutes |
ocr_images |
Images and scanned PDFs → text, lines with confidence and boxes (38 languages incl. Ukrainian) | $1.50 / 1,000 images |
text_to_speech |
Text or PDF/DOCX/HTML → natural speech MP3/WAV/OGG + SRT subtitles (37 voices, 23 languages incl. Ukrainian) | $10 / 1,000 audio minutes ($40 high quality) |
screenshot_website |
Web pages or your HTML → full-page PNG/JPEG/WebP screenshots or PDF; desktop, tablet, mobile; one element by CSS selector | $4 / 1,000 pages |
check_domains |
Bulk WHOIS/RDAP (registrar, expiry, days left), DNS records (A, MX, NS, TXT…), SSL certificate expiry | $2 / 1,000 domains |
extract_video_frames |
Video → frames with timecodes: evenly spaced, every N seconds, exact times, scene changes or keyframes; contact sheet | $1 / 1,000 frames |
Every tool takes public file URLs and a max_charge_usd safety limit per call (default $1).
Option 1 - hosted (no install)
Use Apify's hosted MCP server with exactly these tools:
{
"mcpServers": {
"document-tools": {
"url": "https://mcp.apify.com?tools=ai_admin/document-to-markdown,ai_admin/office-to-pdf,ai_admin/pdf-image-converter,ai_admin/audio-transcriber,ai_admin/image-to-text-ocr,ai_admin/text-to-speech,ai_admin/website-screenshot,ai_admin/domain-whois-dns-ssl,ai_admin/video-frame-extractor"
}
}
}
On first connection your browser opens to sign in to Apify (or pass Authorization: Bearer <APIFY_TOKEN>).
Option 2 - local (stdio)
git clone https://github.com/AndriyVK/-apify-document-tools
cd -- -apify-document-tools/mcp-server
pip install -r requirements.txt
{
"mcpServers": {
"document-tools": {
"command": "python",
"args": ["/path/to/-apify-document-tools/mcp-server/server.py"],
"env": { "APIFY_TOKEN": "your Apify API token" }
}
}
}
Get the token in Apify Console → Settings → API & Integrations. New Apify accounts include free monthly usage credit.
Source
The Actors behind the tools live in the parent folders of this repository (MIT licence).
Apify Document & Media Tools MCP questions
How do I add Apify Document & Media Tools MCP to Claude Code?
Run claude mcp add --transport http apify-document-tools 'https://mcp.apify.com/?tools=ai_admin/document-to-markdown,ai_admin/office-to-pdf,ai_admin/pdf-image-converter,ai_admin/audio-transcriber,ai_admin/image-to-text-ocr,ai_admin/text-to-speech,ai_admin/website-screenshot,ai_admin/domain-whois-dns-ssl,ai_admin/video-frame-extractor,ai_admin/social-video-transcript' in your terminal. Add --scope user to make it available in every project.
How do I add Apify Document & Media Tools MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Apify Document & Media Tools MCP provide?
It exposes 14 tools, including get-actor-run, get-dataset-items, get-key-value-store-record, abort-actor-run, ai_admin--document-to-markdown.
Can I set a spending limit for each tool call?
Yes, every tool accepts a max_charge_usd safety limit per call, which defaults to $1.
How do I authenticate with the local installation?
You need to provide your Apify API token in the environment variables.