MCP.Market

Ollos MCP server

by kelvinbiffi·io.github.kelvinbiffi/ollos-mcp·v0.1.0
No reviews yet

Local, offline transcription, speakers, keyframes, on-screen text and review of any audio or video.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars64 downloads/wk

Reviews

Write one

Nobody has reviewed Ollos yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Ollos tools (10, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • ollos_cancelwrite action

    Stop a queued or running ollos job by jobId — for example when the user changes their mind about a long transcription, or asked for the wrong file. The running stage is aborted (ffmpeg and model inference stop within a second) and the job is marked cancelled; partial artifacts already written stay on disk and are not reused. A job that already finished is reported with its final status and cancell

  • ollos_diarize
  • ollos_frames

    Return contact sheets or individual frames from a finished ollos_keyframes or ollos_read_screen job as images you can look at. Ask for sheets first (each shows 9 timestamped frames); ask for a single frame only when you need a close-up. Default 6 images per call (maxImages, up to 12) to protect the context window. Example: {"jobId":"j_…","sheets":[1,2]} or {"jobId":"j_…","frames":[14]}.

  • ollos_job

    Get the state of a job started by ollos_transcribe, ollos_keyframes, ollos_read_screen, ollos_review or ollos_diarize: stage, percentage, and — once completed — the formatted result plus resource links, so no second call is needed. Poll every few seconds; the server keeps jobs on disk, so a jobId survives a restart (an interrupted job says so instead of hanging). Example: {"jobId":"j_a1b2c3d4e5f6"

  • ollos_keyframes

    Pick the frames of a video that carry information and pack them into 3×3 contact sheets, so you can "watch" an hour of video in a handful of images. Frames are chosen by perceptual-hash change (works on screen recordings, where scene detection sees nothing), hard cuts (window switches, modals), optional anchors, and a floor of one frame every 20 s. Each tile shows its timestamp. Returns sheet reso

  • ollos_probe

    Read what a file, URL or folder actually is, in under a second: kind (video/audio/image), duration, resolution, aspect ratio and which platforms it fits, codecs, fps, audio channels and track count. Use it first, before any other ollos tool, to decide what to run and to detect a Zoom recording folder with one audio track per participant. Never trusts the file extension; a .mp4 without video is rep

  • ollos_read_screen

    OCR the text visible in a video or image and scan it for secrets: API keys, JWTs, bearer tokens, .env lines, private deployment URLs, local URLs, e-mails. Frames are selected as in ollos_keyframes, then read in upscaled tiles (small UI text is unreadable otherwise). Secret findings combine three signals — known patterns, high-entropy tokens, and nearby UI words like "API Key Created" — and are ALW

  • ollos_review

    Check a video before it goes public and return a verdict (ok / warn / block) with findings: loudness vs the platform target (YouTube -14 LUFS) and true peak, silence gaps worth cutting, aspect ratio vs the platform (a 1890×1080 file gets black bars on YouTube), and secrets visible on screen. The secrets check reads frames with OCR and is the slow part; drop it from checks for an instant audio/aspe

  • ollos_search

    Find moments across everything ollos has transcribed or read from screen: "what did we decide about the deadline", "when did the 401 error appear". Hybrid retrieval — BM25 for exact names, acronyms and numbers plus multilingual embeddings for meaning, fused by reciprocal rank — returning up to k passages with timestamp, speaker and source job, never whole transcripts. Scope "all" (default) searche

  • ollos_transcribe

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

no findings
  • Code scan76 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 23 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Ollos compares

Against every graded Media MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 85% of 1,337 Media servers
Tools
10
the typical Media server has 7
Tools that change things
10%
typical: 4%. Fewer write tools means less an agent can break
Downloads a week
64
more than 49% of 365 Media servers with a package

What its tools let an agent do: 9 read · 1 change

Install Ollos in Claude Code, Cursor or VS Code

Runs npx -y ollos-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add ollos-mcp -- npx -y ollos-mcp
Add to Cursor

What the publisher says

From the Ollos repository's README, as published. We do not edit it. Read it on GitHub

ollos-mcp

Eyes and ears for AI agents. Local, offline transcription, keyframes, on-screen text and a pre-publish review of any audio, video or image — as an MCP server, a CLI and a Node library. No Python, no cloud, no API key.

Docs: Tool reference · Design doc — decisions and measurements · Evaluation results · Contributing · Security · Changelog

11 minutes of screencast become 14 contact sheets and 3 KB of text. And it tells you if your API key is visible at 2:50.

npx ollos-mcp            # MCP server on stdio
npx ollos review talk.mp4

Ollos is Galician for eyes.

Why

Agents can't hear or watch. Today you either pay a transcription API, install a Python pipeline, or paste frames by hand. Ollos runs Whisper, speaker segmentation, perceptual-hash keyframing and OCR in Node, through ONNX Runtime, on your machine. The file never leaves it.

It was built for one workflow first — reviewing a screen recording before publishing — and grew into the general case: meetings, lessons, podcasts, downloaded videos.

Install

Node 20+. npm install brings its own ffmpeg (ffmpeg-static); a system ffmpeg is used if present.

Claude Code

claude mcp add ollos -- npx -y ollos-mcp

or in the project's .mcp.json (the same JSON works for Claude Desktop's claudedesktopconfig.json, Cursor's .cursor/mcp.json and Windsurf's mcp_config.json):

{
  "mcpServers": {
    "ollos": { "command": "npx", "args": ["-y", "ollos-mcp"] }
  }
}

VS Code — .vscode/mcp.json uses servers instead of mcpServers:

{
  "servers": {
    "ollos": { "type": "stdio", "command": "npx", "args": ["-y", "ollos-mcp"] }
  }
}

Claude Desktop reads ~/Library/Application Support/Claude/claudedesktopconfig.json on macOS and %APPDATA%\Claude\claudedesktopconfig.json on Windows. Environment variables (OLLOSHOME, OLLOSYTDLP, …) go in an env object next to args; use absolute paths, ~ is not expanded.

CLI

npm i -g ollos-mcp
ollos warmup            # download the default ASR model and VAD (2.75 GB)
ollos warmup --all      # every model: fast ASR, speakers, search, OCR data (3.3 GB total)
ollos doctor            # check ffmpeg, models, free memory, cores

Models download on first use into ~/.ollos/models. Set OLLOS_OFFLINE=1 afterwards to forbid all network access.

Tools

Ten tools, one per distinct contract. Long work never blocks: it returns a jobId you poll.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Ollos: common questions

Is Ollos MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Ollos safety report
How do I install Ollos?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Ollos need an API key?
No secret keys are declared. It reads 4 settings from the environment.
Is Ollos maintained?
The last commit was 43 days ago (2026-09-22). The latest release is v0.1.0.
What can I use instead of Ollos?
Servers from other publishers that do the same job: Transcription MCP server, FFmpeg MCP server and Transloadit Media Processing MCP server. Compare all Ollos alternatives.
How does Ollos compare with other Media MCP servers?
safety score 92/100 (higher than 85% of 1,337 Media servers); tools 10 (the typical Media server has 7); tools that change things 10% (typical: 4%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Ollos

Same job from other publishers: the closest match first, then the best rated.

All Ollos alternatives →
  • Transcription
    Transcribe audio and video and work with your transcript library from any AI app. 119 languages.
    A
  • FFmpeg
    Trim, convert, resize, compress, and remix audio and video.
    A
  • Transloadit Media Processing
    Process video, audio, images and documents with Transloadit Robots. Connect by URL with OAuth.
    A
  • OpenScreen
    Screen recorder and video editor. Agents record, trim, zoom, caption, add effects and export.
    C
  • three.ws Audio
    Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents.
    More from nirholas →
    B