Media Context Mcp

io.github.vishalguptaxPublished by GitHub account vishalguptaxv0.1.4Updated Oct 24, 2026

Local MCP server to analyze video, audio & images: frames, transcripts, on-screen text.

VerifiedSTDIODesktop onlyFiles & StorageMedia & Design

Overview

AI-generated overview

Local MCP server that turns video, audio and image files or links into model-readable context: sampled frames, transcripts and on-screen text.

What you can do
  • Analyze a video, audio file or image from a local path or an http(s) URL, with automatic type detection
  • Sample video frames as contact sheets, individual stills, scene-change frames or a dense filmstrip, with cropping, time windows and frame limits
  • Transcribe speech from audio or video, choosing a Whisper model size
  • Extract on-screen text with OCR, including language selection and page-segmentation options
  • Track an on-screen number and report jump-back glitches with timestamps
  • Check which local helper dependencies are installed and ready
When to use it
Useful when you want an assistant to summarize a screen recording, read an error shown in a video or screenshot, walk through a UI flow, transcribe a meeting or voice note, or pull context from a YouTube or Vimeo link without uploading the media.
Requirements
Runs as a local process launched with npx, so Node.js 18+ is needed on Windows, macOS or Linux. A one-time setup command installs the local helpers (keyframes, link fetching, OCR; audio transcription is optional). No API keys or environment variables are declared.
Before you install
The setup command installs helper software through your OS package manager, so review what it adds and use the uninstall option to remove it. Media from URLs is downloaded to your machine, subject to the configured duration and file-size limits. Analysis runs locally and the README states nothing is uploaded, but the resulting frames and transcripts are passed to your assistant's model.

Installation

In SourceWeft

  1. Open Media Context Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[media-context-mcp — local media analysis for AI assistants]

[npm version] [npm downloads] [license] [node]

Give your AI assistant eyes and ears.
Analyze any video, audio, or image — locally, right inside your editor.

Install  ·  Capabilities  ·  Modes  ·  Examples  ·  Tools  ·  Options  ·  Docs


LLMs read text and glance at a single image — but they can't watch a video or listen to audio. media-context-mcp closes that gap. Hand it a file or a link and it returns clean, model-ready context — keyframes, a transcript, or the text on screen — entirely on your machine. Nothing is uploaded.

[A 10-second clip turned into one contact sheet of keyframes]

A 10-second clip becomes one tidy contact sheet your model reads in order — not hundreds of stills.


🚀 Install

Two steps — add the server, then install the local helpers it uses.

1 · Add the server to your client

bash
# Claude Codeclaude mcp add media-context -- npx -y media-context-mcp

The launch command is always npx -y media-context-mcp. Pick your client:

Claude Desktop

Settings → Developer → Edit Config (claude_desktop_config.json):

json
{  "mcpServers": {    "media-context": { "command": "npx", "args": ["-y", "media-context-mcp"] }  }}
Cursor

~/.cursor/mcp.json (global) or .cursor/mcp.json (per-project):

json
{  "mcpServers": {    "media-context": { "command": "npx", "args": ["-y", "media-context-mcp"] }  }}
VS Code (GitHub Copilot, agent mode)

.vscode/mcp.json — VS Code uses the servers key:

json
{  "servers": {    "media-context": { "command": "npx", "args": ["-y", "media-context-mcp"] }  }}
Windsurf

~/.codeium/windsurf/mcp_config.json:

json
{  "mcpServers": {    "media-context": { "command": "npx", "args": ["-y", "media-context-mcp"] }  }}
Cline / Roo Code

cline_mcp_settings.json (the extension's MCP settings):

json
{  "mcpServers": {    "media-context": { "command": "npx", "args": ["-y", "media-context-mcp"] }  }}
Kiro

.kiro/settings/mcp.json (project) or ~/.kiro/settings/mcp.json (user):

json
{  "mcpServers": {    "media-context": { "command": "npx", "args": ["-y", "media-context-mcp"] }  }}
Gemini CLI

~/.gemini/settings.json:

json
{  "mcpServers": {    "media-context": { "command": "npx", "args": ["-y", "media-context-mcp"] }  }}
Zed

settings.json — Zed uses context_servers:

json
{  "context_servers": {    "media-context": { "command": { "path": "npx", "args": ["-y", "media-context-mcp"] } }  }}
Codex CLI

~/.codex/config.toml:

toml
[mcp_servers.media-context]command = "npx"args = ["-y", "media-context-mcp"]
JetBrains AI Assistant

Settings → Tools → AI Assistant → Model Context Protocol → Add, then use command npx with args -y media-context-mcp.

Tip: in Claude Code you can install it as a plugin instead — run /plugin marketplace add vishalguptax/media-context-mcp, then /plugin install media-context. To share with a team, install per-project: --scope project (writes .mcp.json) or commit a .cursor/mcp.json in the repo.

2 · Install the local helpers

One command sets up everything the server uses, via your OS package manager:

bash
npx media-context-mcp setup          # core: keyframes, links, on-screen textnpx media-context-mcp setup --audio  # also enable transcription

The server finds the helpers automatically afterward — no extra configuration. Run check_media_deps to see what's ready, and setup --uninstall to remove them. (Install by hand →)

3 · Ask

“Summarize demo.mp4.”

✨ Capabilities

VideoKeyframe overview, full-size stills, scene detection, or a dense filmstrip that catches split-second glitches
AudioSpeech turned into text — clips, voice notes, meetings, podcasts
ImagesThe picture, plus the exact text shown on screen
AnywhereLocal files or links — YouTube, Vimeo, and 1000+ sites
PrivateRuns on your machine. No API keys, no uploads
EfficientA long clip becomes a couple of images, not hundreds

🎞️ Modes

analyze_media auto-detects audio and images. For video, choose how frames are sampled:

ModeBest for
sheet (default)A cheap overview — frames tiled into one or two contact sheets
framesDetail on specific moments — individual full-size stills
scenesSlide decks & static screencasts — only scene-change frames
filmstripCatching a sub-second UI glitch — a dense, near-native-rate strip

💬 Examples

Just ask in plain language — the assistant picks the right options.

You askWhat you get
“Summarize demo.mp4.”A quick overview from sampled keyframes
“What error does bug.mp4 show at the end?”The exact on-screen text, read back
“Walk me through the UI flow in onboarding.mov.”Step-by-step from scene-change frames
“Transcribe standup.m4a and list action items.”A local transcript
“Summarize https://youtu.be/… with the transcript.”Fetched and transcribed
“Read the error in this screenshot crash.png.”The picture plus its exact text
“Find where the slider in ui.mp4 flickers ~0:06.”The exact frame of a sub-second glitch

🧰 Tools

ToolWhat it does
analyze_mediaTurn a video, audio, or image — file or URL — into model-readable context. Auto-detects the type and supports cropping, time windows, language, and sampling rate.
check_media_depsReport which capabilities are ready on this machine.

Every call runs locally and cleans up after itself.

⚙️ Options

Your assistant fills these in for you, but you can steer it (“use filmstrip mode”, “crop to the toolbar”).

Full analyze_media parameters
ParamDefaultDescription
source—Local file path (video/audio/image) or http(s) URL
context—A note framing the analysis; echoed atop the summary
detail—high = readable stills for screen recordings; low = cheap overview
modesheetsheet · frames · scenes · filmstrip
formatwebpwebp (smallest) · jpeg · png (crisp text)
maxFrames30Upper bound on sampled frames
grid5Tiles per row/column for contact-sheet modes
scale320Per-frame width in px — lower = fewer tokens
sceneThreshold0.4Scene-change sensitivity (scenes mode)
fpsautoExplicit sampling rate; pair high with filmstrip
crop—{x,y,width,height} (pixels, or 0–1 fractions) to zoom a region
stripRows18Tiles per image in filmstrip mode
startSec / endSec—Restrict to a time window
transcriptfalseAlso produce a transcript (video)
whisperModelsmalltiny · base · small · medium · large
ocrfalseExtract on-screen text
ocrLangengLanguage code(s), e.g. eng+deu
ocrPsm3Page-segmentation: 3 auto · 6 block · 11 sparse
detectJumpsfalseTrack an on-screen number and report jump-back glitches with timestamps
maxDurationSec3600Reject URL downloads longer than this
maxFileSizeMb500Abort a URL download past this size

Worked recipes for each are in the usage guide.

❓ FAQ

Can an LLM watch a video? Not directly — models take images and text, not video. This server turns the video into frames and a transcript it can read.

Does anything get uploaded? No. Everything runs on your machine; no keys, no cloud.

Which clients work? Any MCP client — Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Cline, Kiro, Gemini CLI, JetBrains, Zed, Codex.

Does it handle YouTube and other links? Yes.

How much does it cost? It's free and open source.

📋 Requirements

Node.js 18+, on Windows, macOS, or Linux. The one-time npx media-context-mcp setup installs everything else.

🛠️ Development

bash
npm installnpm run buildnpm test

Issues and PRs welcome — see the usage guide for the architecture.

📄 License

Apache-2.0 © Vishal Gupta

Source: README.md at commit 2cc68be

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.4LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts