{"name":"io.github.kelvinbiffi/ollos-mcp","slug":"kelvinbiffi-ollos-mcp","title":null,"description":"Local, offline transcription, speakers, keyframes, on-screen text and review of any audio or video.","url":"https://mcp.market/server/kelvinbiffi-ollos-mcp","rating":null,"grade":"A","score":92,"certified":false,"status":"active","category":"media","tags":["media"],"presence":{"score":27,"stars":0,"forks":0,"downloads_week":64,"last_push_at":"2026-09-15T22:11:47.000Z","license":"Apache-2.0"},"uptime":null,"claimed":false,"transport":"npm","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/kelvinbiffi/ollos-mcp","website":"https://github.com/kelvinbiffi/ollos-mcp#readme","version":"0.1.0","remotes":[],"packages":[{"registryType":"npm","identifier":"ollos-mcp","version":"0.1.0","transport":{"type":"stdio"},"environmentVariables":[{"description":"Where jobs, cache and models live. Default ~/.ollos","name":"OLLOS_HOME"},{"description":"Set to 1 to forbid any network access (models must be warmed up first)","name":"OLLOS_OFFLINE"},{"description":"Path to a yt-dlp binary for video-site URLs (default: found on PATH)","name":"OLLOS_YTDLP"},{"description":"Allow-listed yt-dlp flags, e.g. --no-check-certificates behind a TLS-intercepting proxy","name":"OLLOS_YTDLP_ARGS"}]}],"tools":[{"name":"ollos_cancel","description":"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","write_action":true,"price_micros":0,"input_schema":null},{"name":"ollos_diarize","description":"","write_action":false,"price_micros":0,"input_schema":null},{"name":"ollos_frames","description":"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]}.","write_action":false,"price_micros":0,"input_schema":null},{"name":"ollos_job","description":"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\"","write_action":false,"price_micros":0,"input_schema":null},{"name":"ollos_keyframes","description":"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","write_action":false,"price_micros":0,"input_schema":null},{"name":"ollos_probe","description":"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","write_action":false,"price_micros":0,"input_schema":null},{"name":"ollos_read_screen","description":"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","write_action":false,"price_micros":0,"input_schema":null},{"name":"ollos_review","description":"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","write_action":false,"price_micros":0,"input_schema":null},{"name":"ollos_search","description":"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","write_action":false,"price_micros":0,"input_schema":null},{"name":"ollos_transcribe","description":"","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":92,"grade":"A","scanned_at":"2026-09-19T21:08:20.307Z","report":{"scannerVersion":"0.1.8","scannedAt":"2026-09-19T21:08:20.284Z","components":{"code":{"score":25,"max":25,"notes":["76 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":15,"max":15,"notes":["last push 4 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[],"inputs":{"packages":[{"registryType":"npm","identifier":"ollos-mcp","version":"0.1.0","found":true,"license":"Apache-2.0","hasInstallScripts":false,"dependencyCount":6,"publishedAt":"2026-09-15T20:04:10.463Z","repositoryUrl":"git+https://github.com/kelvinbiffi/ollos-mcp.git","weeklyDownloads":64}],"repo":{"found":true,"owner":"kelvinbiffi","repo":"ollos-mcp","archived":false,"pushedAt":"2026-09-15T22:11:47Z","stars":0,"forks":0,"openIssues":3,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/16124264?v=4","ownerCreatedAt":"2015-12-02T20:22:34Z","license":"Apache-2.0"},"icon":{"url":"https://avatars.githubusercontent.com/u/16124264?v=4&s=128","source":"registry"},"presence":{"stars":0,"forks":0,"downloadsWeek":64,"license":"Apache-2.0","lastPushAt":"2026-09-15T22:11:47.000Z","score":27}}}},"grade_history":[],"reviews":[]}