Skip to content
Agentmart
Submit a tool

Ocular Audio MCP

MCP server for video transcripts, screenshots, and OCR on YouTube and web videos.

Connector by RayAKaan · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/rayakaan-ocular-audio-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

MCP server for video transcripts, screenshots, and OCR on YouTube and web videos.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
27 read · 1 write · 1 delete · 4 not yet classified
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 33

Read from the source code; the running server may list different tools.

Read 27 · Look things up without changing anything.

  • analyze_ocular_audio_batch
  • crop_ocular_audio_video_frame
  • get_ocular_audio_audit
  • get_ocular_audio_batch
  • get_ocular_audio_capabilities
  • get_ocular_audio_chapters
  • get_ocular_audio_contract
  • get_ocular_audio_health
  • get_ocular_audio_identity
  • get_ocular_audio_metadata
  • get_ocular_audio_transcript
  • get_ocular_audio_video_context
Show 15 more tools
  • get_ocular_audio_video_frame
  • get_ocular_audio_video_frame_burst
  • get_ocular_audio_video_screenshots
  • get_ocular_audio_video_timeline
  • inspect_ocular_audio_moment
  • inspect_ocular_audio_multimodal_moment
  • inspect_ocular_audio_source
  • list_ocular_audio_batches
  • list_ocular_audio_cache
  • query_ocular_audio_evidence
  • search_ocular_audio_cache
  • search_ocular_audio_hybrid
  • search_ocular_audio_video
  • search_ocular_audio_videos
  • search_ocular_audio_visuals

Write 1 · Create, change, send or run things.

  • index_ocular_audio_video_visuals

Delete 1 · Delete, drop, revoke or wipe things.

  • clear_ocular_audio_cache

Not yet classified 4 · We could not tell from the name and description.

  • analyze_ocular_audio_multimodal
  • compare_ocular_audio_videos
  • plan_ocular_audio_analysis
  • run_ocular_audio_analysis

Files it touches

  • Any path the agent passes to its tools

Tools (33)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • analyze_ocular_audio_batch

    Analyze a bounded source collection using the selected capability mode.

  • analyze_ocular_audio_multimodal

    Build and rank unified evidence moments under a bounded mode policy.

  • clear_ocular_audio_cache

    Clears cached video data. Args: video_id: Optional video ID to clear specific video. If empty, clears all cache.

  • compare_ocular_audio_videos

    Build a comparable per-video scorecard under the selected mode budget.

  • crop_ocular_audio_video_frame

    Extract and crop a region from a timestamped frame using normalized or pixel coordinates.

  • get_ocular_audio_audit

    Return recent local execution audit records.

  • get_ocular_audio_batch

    Retrieve a persisted Phase 6 batch result by deterministic batch ID.

  • get_ocular_audio_capabilities

    Returns system capabilities and dependency status. Use this tool to check what features are available before making other requests. Returns information about Python, FFmpeg, Whisper, Tesseract, OpenCV, and cookie status.

  • get_ocular_audio_chapters

    Extracts only video chapters with timestamps. Use this when you need to understand the video structure without getting the full transcript. Returns chapter titles with start times in [MM:SS] format.

  • get_ocular_audio_contract

    Return the machine-readable MCP contract and current capability surface.

  • get_ocular_audio_health

    Return dependency, cache, and production-readiness health checks.

  • get_ocular_audio_identity

    Return the authenticated HTTP principal without exposing bearer credentials.

  • get_ocular_audio_metadata

    Extracts only video metadata (title, creator, duration, views, chapters) without transcript. Use this when you need quick video info without the full transcript. Much faster than get_ocular_audio_transcript if you only need metadata.

  • get_ocular_audio_transcript

    Extracts the complete transcript, video chapters, and metadata of any YouTube or general Web video. This is an advanced, fully asynchronous, production-grade hybrid engine: 1. Checks local cache first (instantaneous, 0.01s). 2. Fetches subtitles asynchronously with cookie-authentication (works primarily on YouTube). 3. Falls back to local Whisper transcription running in a background executor thread for general web videos (Vimeo, Twitter, etc.) or YouTube videos without captions. Args: url: The full YouTube or Web video URL. use_local_whisper: Enable offline local transcribing fal…

  • get_ocular_audio_video_context

    Extracts transcript, metadata, and optional intelligent screenshots from a video. Automatically analyzes the transcript to find visually important moments and captures screenshots at those timestamps. Returns everything combined. Modes: - "auto" (default): Adapts screenshot count to video length and content importance. - "overview": Transcript and metadata only, no screenshots. Fastest. - "balanced": Captures screenshots only at visually important moments (strong signals). - "deep": Captures screenshots at every visually significant moment (all signals). Args: url: The full YouT…

Show 18 more tools
  • get_ocular_audio_video_frame

    Return one higher-resolution frame plus machine-readable frame metadata.

  • get_ocular_audio_video_frame_burst

    Return a bounded chronological burst of high-resolution frames around a moment.

  • get_ocular_audio_video_screenshots

    Extracts high-quality, low-resolution screenshots at specific timestamps directly from any YouTube or Web video WITHOUT downloading the entire file (uses HTTP range-seeking streaming). This runs asynchronously in a background thread to prevent blocking concurrent MCP requests. Args: url: The full YouTube or Web video URL. timestamps_secs: A list of timestamps in seconds to screenshot (e.g., [45, 120, 300]) enable_ocr: If True, run OCR on each captured frame to extract visible text.

  • get_ocular_audio_video_timeline

    Return timestamped transcript evidence for a bounded section of a video.

  • index_ocular_audio_video_visuals

    Build a persistent visual evidence index under a mode-specific sampling budget.

  • inspect_ocular_audio_moment

    Inspect one moment with the nearest transcript evidence and a targeted frame.

  • inspect_ocular_audio_multimodal_moment

    Inspect one timestamp as a unified transcript, visual, and OCR evidence moment.

  • inspect_ocular_audio_source

    Resolve a URL or local media file without downloading or analyzing it.

  • list_ocular_audio_batches

    List recent persisted batch results without loading individual media.

  • list_ocular_audio_cache

    Lists all cached videos with their metadata. Shows video titles, uploaders, duration, and when they were cached. Use this to see what videos have been previously processed.

  • plan_ocular_audio_analysis

    Build a mode-aware plan with explicit evidence, time, and retry budgets.

  • query_ocular_audio_evidence

    Query canonical evidence records by modality, timestamp range, and text.

  • run_ocular_audio_analysis

    Execute a mode-aware, bounded plan using existing evidence tools.

  • search_ocular_audio_cache

    Search all locally cached transcripts and return ranked timestamped evidence.

  • search_ocular_audio_hybrid

    Search transcript and visual OCR evidence under a bounded capability policy.

  • search_ocular_audio_video

    Search a video's timestamped transcript evidence and return ranked moments.

  • search_ocular_audio_videos

    Search multimodal evidence across multiple videos under one mode policy.

  • search_ocular_audio_visuals

    Search indexed visual evidence under the selected evidence budget.

Compare and alternatives

    Featured in

    Signals

    Stars
    1
    Forks
    0
    Open issues
    0
    Last commit
    Oct 12, 2026 (16 days ago)
    Last release
    Jul 11, 2026 (3 months ago)

    From GitHub (fetched Oct 24, 2026).

    Details

    Registry name
    io.github.RayAKaan/ocular-audio-mcp
    Version
    1.1.2
    Auth
    No auth
    Packages
    npm ocular-audio-mcp
    License
    MIT
    Repository
    github.com/RayAKaan/OcularAudio-MCP
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026
    Source
    Official MCP Registrygithub-graphql
    Cite this page

    Ocular Audio MCP. Agent Mart. https://agentmart.dev/connectors/rayakaan-ocular-audio-mcp (last updated 2026-10-24)