Video URL Analyzer

Analyze YouTube/TikTok/Instagram videos: transcripts, AI insights, tutorial extraction

Connector by u2n4 · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 4

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/u2n4-video-url-analyzer-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.

About

Analyze YouTube/TikTok/Instagram videos: transcripts, AI insights, tutorial extraction

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: 16 read · 1 write · 1 delete
Secrets: None asked for
Install scripts: Not scanned yet
Runs as: Python package

Tools by what they do 18

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

Read 16 · Look things up without changing anything.

analyze_video
analyze_video_segment
ask_about_video
ask_video_context
check_analysis_job
cleanup_video_cache
find_video_moments
get_transcript
get_video_clip
get_video_evidence_asset
get_video_frame
list_video_contexts

Show 4 more tools

list_video_sources
prepare_slideshow_assets
prepare_video_context
watch_and_analyze

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

execute_tutorial_steps

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

delete_video_context

Tools (18)

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

analyze_video
Analyze a video or photo/slideshow post from YouTube, TikTok, or Instagram. Provides comprehensive audio + visual analysis using Gemini AI. Works with videos AND photo/slideshow posts on TikTok, Instagram, and YouTube community posts. YouTube videos are analyzed directly and return the result immediately. TikTok and Instagram videos are processed in the background — the tool returns a job_id. Use check_analysis_job(job_id) to poll for the result. Args: url: The video URL (YouTube, TikTok, Instagram, or other). prompt: Custom analysis prompt. Defaults to comprehensive analysis. mo…
analyze_video_segment
Analyze only a selected video segment. Uses Gemini video_metadata clipping when available. Gemini performs video/audio/visual reasoning. detail controls model + max_output_tokens + thinking/media config.
ask_about_video
Ask a specific question about a video or photo/slideshow post. Works with videos AND photo/slideshow posts on TikTok, Instagram, and YouTube community posts. YouTube returns the answer immediately. TikTok/Instagram return a job_id — use check_analysis_job(job_id) to poll for the result. Args: url: The video URL (YouTube, TikTok, Instagram, or other). question: Your question about the video. model: Gemini model to use. Defaults to gemini-3.5-flash. Returns: Answer text (YouTube) or JSON with job_id (TikTok/Instagram).
ask_video_context
Answer a question from saved video context without Gemini by default.
check_analysis_job
Check the status of a background video analysis job. When analyze_video, get_transcript, ask_about_video, or watch_and_analyze returns a job_id (for TikTok/Instagram videos), use this tool to poll for the result. Keep calling until status is "completed" or "failed". Args: job_id: The job ID returned by the analysis tool. Returns: JSON with status ("processing", "completed", or "failed") and the result when done.
cleanup_video_cache
Inspect or clean managed video cache files. Safe dry-run by default.
delete_video_context
Delete one saved local video context file.
execute_tutorial_steps
Review or execute tutorial steps extracted by watch_and_analyze. SAFETY: By default (confirm=false), this only shows a summary of what WOULD be executed. Set confirm=true ONLY after reviewing the steps. Args: steps_json: The JSON output from watch_and_analyze (copy the full analysis field). confirm: If false (default), shows a review summary. If true, executes the steps. Returns: Review summary (confirm=false) or execution log with success/failure per step (confirm=true).
find_video_moments
Find moments in a video matching a semantic query. Gemini performs the video/audio/visual reasoning. detail controls model + max_output_tokens + thinking/media config. compact is default and returns concise structured JSON.
get_transcript
Extract speech transcript from a video or slideshow audio track. YouTube returns the result immediately. TikTok/Instagram return a job_id — use check_analysis_job(job_id) to poll for the result. Slideshows without audio return a structured slideshow_no_audio response. Args: url: The video URL (YouTube, TikTok, Instagram, or other). lang: Language hint (e.g., 'en', 'ar', 'auto'). Defaults to auto-detect. model: Gemini model to use. Defaults to gemini-3.5-flash. Returns: Transcript text (YouTube) or JSON with job_id (TikTok/Instagram).
get_video_clip
Extract a local video clip under 30 seconds and return metadata.
get_video_evidence_asset
Find saved visual evidence and return a local frame/clip reference.
get_video_frame
Extract a local still frame and return compact asset metadata.
list_video_contexts
List saved local video context files.
list_video_sources
List cached video sources, contexts, and assets. Never calls Gemini.

Show 3 more tools

prepare_slideshow_assets
Return slideshow images as ordered MCP image blocks for client-side vision. This tool does not call Gemini. It downloads TikTok Photo Mode, Instagram photo/carousel posts, or YouTube community post images, then returns each image directly to the MCP client with an explicit image_index label. Use it when you want Claude/the client AI to inspect the images itself instead of receiving a Gemini-generated analysis. Args: url: TikTok Photo Mode, Instagram photo/carousel, or YouTube community URL. include_audio: If true and a slideshow audio track exists, include it as an MCP audio …
prepare_video_context
Analyze a whole video once and save a local structured context.
watch_and_analyze
Watch a video tutorial and extract all technical steps, commands, and code. Downloads the video, analyzes it with Gemini AI, and returns structured JSON with every command, code snippet, file path, and tool mentioned. YouTube returns the result immediately. TikTok/Instagram return a job_id — use check_analysis_job(job_id) to poll for the result. This tool ONLY analyzes — it does NOT execute anything. Use execute_tutorial_steps to run the extracted steps after review. Args: url: Video URL (YouTube, TikTok, Instagram). lang: Language hint (e.g., 'en', 'ar', 'auto'). Defaults to auto-d…

Signals

Stars: 4
Forks: 0
Open issues: 0
Weekly downloads: 73
Last commit: May 21, 2026 (5 months ago)
Last release: May 17, 2026 (5 months ago)
Last package publish: May 21, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.u2n4/video-url-analyzer-mcp
Version: 1.5.1
Auth: No auth
Packages: pypi video-url-analyzer-mcp
License: MIT
Repository: github.com/u2n4/video-url-analyzer-mcp
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql

More from u2n4

Cite this page

Video URL Analyzer MCP server. Agent Mart. https://agentmart.dev/connectors/u2n4-video-url-analyzer-mcp (last updated 2026-10-24)