joaoestella avatar

mediasense

joaoestella/mediasense

Let Claude listen to audio and watch video: transcribe, summarize and edit recordings and links.

GitHub stars
1
tools
12
transport
STDIO
env var
1
last updated
Nov 10, 2026

Tools

12 tools

Public tool metadata for what this MCP can expose to an agent.

understand_mediaone call: download link, transcribe, key frames + speech per shot, post title/description

one call: download link, transcribe, key frames + speech per shot, post title/description

No parameter schema in public metadata yet.

transcribespeech → <file>.transcript.json with word timestamps; vocabulary fixes brand names

speech → <file>.transcript.json with word timestamps; vocabulary fixes brand names

No parameter schema in public metadata yet.

read_transcriptread a time range of a transcript

read a time range of a transcript

No parameter schema in public metadata yet.

search_transcriptfind every time a phrase is said

find every time a phrase is said

No parameter schema in public metadata yet.

plan_editcut phrases, passages, fillers, silences or ranges; preview the plan

cut phrases, passages, fillers, silences or ranges; preview the plan

No parameter schema in public metadata yet.

render_editrender the planned edit after preview

render the planned edit after preview

No parameter schema in public metadata yet.

export_transcriptexport transcript as SRT, VTT, TXT, CSV or JSON

export transcript as SRT, VTT, TXT, CSV or JSON

No parameter schema in public metadata yet.

place_audioinsert a clip at a timestamp (mix / duck / replace)

insert a clip at a timestamp (mix / duck / replace)

No parameter schema in public metadata yet.

watch_videogenerate contact sheets of a video

generate contact sheets of a video

No parameter schema in public metadata yet.

get_frameget one frame at a given time

get one frame at a given time

No parameter schema in public metadata yet.

media_infoduration, resolution, fps, streams

duration, resolution, fps, streams

No parameter schema in public metadata yet.

check_jobresult of long work: new videos and the first run reply "still working" and finish in the background

result of long work: new videos and the first run reply "still working" and finish in the background

No parameter schema in public metadata yet.

Sponsors

Configuration

MEDIASENSE_COOKIES_FROM_BROWSER

Optional: browser to read cookies from (chrome, firefox, edge…) for links that need a login.

Readme

mediasense

PyPI Python CI License: MIT

Give Claude ears and eyes. Claude can't listen to audio or watch videos on its own; with mediasense it can. Point at a voice message, podcast, recording or meeting, or paste a TikTok, YouTube or Instagram link, in Claude Code or Claude Desktop and ask in plain language. Claude can then transcribe it, summarize it, explain what happens, find the moment something is said, or edit it.


View the full README on GitHub

Details

Repository
github.com/joaoestella/mediasense
Website
joaoestella.github.io/mediasense
Category
Media & Entertainment
Package
mediasense
Transport
STDIO
Registry
MCP registry, active

Related Media & Entertainment MCP servers

View all
1malkreide avatarSrgssr Mcpmalkreide/srgssr-mcpSRG SSR weather, video, audio, EPG, Polis1stars
2rendobar avatarRendobarrendobar/mcpTransform video, audio and images, and generate media from prompts. FFmpeg, captions, models.0stars
3socialneuron avatarMcp Serversocialneuron/mcp-server52 MCP tools for AI social media: create, distribute, analyze, and optimize content.0stars
40xkaroshi avatarContendeo0xkaroshi/contendeo-mcpMultimodal video analysis MCP — transcription, vision, and OCR for any video URL.0stars
5avotsai avataravotsavotsai/avots-mcpImage, video, audio, face-swap, talking avatars and chat across 300+ AI models, one balance.0stars
6abrahimceylan avatarKreatixabrahimceylan/kreatix-mcpSchedule and publish posts to Instagram, TikTok, YouTube, Facebook, X, LinkedIn and Pinterest.0stars