Receives incoming photos, documents, and videos via Telegram (through prime-tg) into the media pipeline's inbox, where they are automatically picked up and processed by the local inbox watch.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mp-mcp transcribe inbox/voice-message.m4a to text"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Open-source media processing stack for Prime Agent, packaged after the Z-Rea delivery pattern: one CLI, one MCP server, one agent skill, installed into the agent's own subdirectory and triggered automatically when media arrives.
Input | Engine | Output |
video (mp4/mov/mkv/webm) | FFmpeg | normalized mp4 (h264+aac), audio wav, keyframe thumbnails |
audio (wav/mp3/m4a/ogg/flac) | FFmpeg + faster-whisper | transcript (txt/srt/vtt), 16 kHz mono wav |
image (png/jpg/webp/gif) | Pillow + RapidOCR (PP-OCRv4) | OCR text, resized/normalized png, description via LiteLLM vision |
any media | Pollinations, Gemini or LiteLLM | translation of extracted text (EN/TR default), keyless by default |
No GPU. No torch. ARM-native (aarch64). CPU-only, int8 quantized Whisper.
Related MCP server: mcp-ffmpeg
media-pipeline/
bin/mp # CLI (process / probe / watch / translate)
bin/mp-mcp # MCP server (stdio JSON-RPC)
skills/media-pipeline/SKILL.md
skills/media-pipeline/references/*.md
inbox/ # drop zone: anything here is processed
work/ # intermediate
outbox/ # results
failures/ # inputs that failed
logs/./install.shWrites the skill to the agent skill directory, registers the MCP server in the agent config, and creates the inbox/outbox layout under this repo.
Two triggers, both agent-scope:
Local inbox watch - systemd path unit mp-inbox.path fires when a file
lands in inbox/.
Telegram - prime-tg saves an incoming photo/document/video into the
inbox and the same path unit picks it up.
MIT. Public repo content is English only.
This server cannot be deployed
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.
Hosted MCP tools for FFmpeg-style video and audio processing through FFMPEG API.
Local ML: speech to text (SRT/VTT), text embeddings, reranking, similarity, entities, zero-shot.
