What it does
The tools cover document conversion to Markdown and PDF/PDF-A, OCR in 11 to 38 languages depending on the Actor, transcription with Whisper large-v3 in 99 languages, social video transcripts and translation, text to speech with 37 neural voices, website screenshots, bulk domain WHOIS, DNS and SSL checks, and video frame extraction.
Someone working with business documents, subtitles or media files, or an AI agent that needs file-handling tools, would reach for it. The Actors can be called from code or added to an agent through a hosted MCP endpoint that needs no installation.
The Actors run in the cloud from Apify Store, with no setup. Locally, the MCP server runs over stdio from the mcp-server folder, and each Actor folder is self-contained with its own Dockerfile, tests and source. Bug reports with a sample file can be filed as GitHub issues.
Limitations and requirements
Local runs need Tesseract (eng, ukr, rus), LibreOffice, FFmpeg, Chromium and the packages listed in requirements.txt. Text to Speech uses the Piper engine, licensed under GPL-3.0, as a separate package.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 16 Nov 2026 · its page on the source
Document & media tools (Apify)
Documents to Markdown/PDF, OCR, video and audio transcripts, TTS, screenshots, domains, frames.
v0.4.0As shown on registry.modelcontextprotocol.io when we last read it