Remote MCP Server · Live

Give your agent eyes.

Claude reads a video's transcript — it never sees the frames. Contendeo turns any video URL into structured context: a Groq Whisper Turbo transcript, Claude Vision on keyframes, and Tesseract OCR, merged into one JSON.

Add as custom connector in Claude

https://contendeo.app/mcp/

Connect to Claude → See real output →

Supports

YouTube

Instagram

Vimeo

Twitter / X

TikTok

Direct MP4 URL

// the asymmetry problem

Transcripts miss half the video.

When a speaker says "look at this chart" and points at a number on screen, a transcript-only tool loses the number. Contendeo returns it.

Transcript-only output audio → text

"The speaker discusses Claude Opus 4.7 benchmarks, mentioning it performs well on software engineering tasks and shows improvements over previous models. He talks about office-related evaluations and compares it to GPT models and earlier Claude releases. Overall the tone is positive about the release."

Contendeo deep_analyze output audio + vision + ocr

{
  "type": "benchmark_table",
  "timestamp": "05:41",
  "extracted_data": {
    "swe_bench_pro": {
      "opus_4_7": 64.3,
      "opus_4_6": 53.4,
      "gpt_5_4":   57.7
    }
  }
}

Full side-by-side breakdown, with the source clip →

// how it works

Three steps. No infrastructure.

Connect once. Then paste any supported URL into Claude and ask for transcription or analysis.

STEP 01

Add the connector

In Claude, add https://contendeo.app/mcp/ as a custom connector and sign in with Google. About a minute, once.

STEP 02

Paste any video URL

Supports YouTube, Instagram Reels, Vimeo, Twitter/X, TikTok, and direct MP4 URLs. Up to 2-hour runtime.

STEP 03

Get structured intelligence

Timestamped transcript, keyframe descriptions, extracted chart data, OCR'd text, entities mapped — one JSON payload Claude reasons over.

yt-dlp

Fetch source from any supported URL

ffmpeg

Demux audio + sample keyframes

in parallel

Groq Whisper Turbo

Timestamped transcript

Tesseract OCR

Text burned into frames

Claude Vision

Scene describe + chart extraction

Unified output

One JSON the LLM can reason over

// tools

Four tools. Purpose-built.

Each tool is optimized for a different shape of video comprehension. Credits are refunded on failure, and cache hits are free.

quick_transcribe

TRANSCRIPTION ONLY (no visual analysis). Best for interviews, podcasts, and any content where text is enough. For vision, OCR, charts, or keyframe analysis, use deep_analyze instead.

1 credit

deep_analyze

PRIMARY tool for video understanding. Full multimodal pipeline: transcript + vision + OCR + entity extraction. Returns summary, key claims, visual assets, and charts as structured data.

5 credits

clip_context

Analyze a specific segment by timestamp range. Default is full multimodal (3 credits — transcript + vision + OCR on the range). Pass mode='quick' for transcript-only (1 credit). Pay the flat rate regardless of full video length.

3 credits (default)

batch_analyze

Up to 10 videos at once with cross-video synthesis — common themes, entity overlap, contradicting claims. Default is mode='quick' (1 credit each) for bulk transcription; pass mode='deep' for multimodal across all (5 credits each). 10% off on 5+ videos.

per video + bulk discount

// pricing

Credit-based. No wasted spend.

Pay only for processing. Cache hits are free, failures are refunded automatically, unused credits roll over on paid plans.

Free

10 credits on signup

All four tools
No card required
Cache hits always free
Auto-refund on failure

Get started

RECOMMENDED

Pro

$12

per month

100 credits / month
Priority processing queue
Rollover up to 200 credits
All four tools

Start Pro →

Power

$39

per month

500 credits / month
Batch processing enabled
Webhooks for async jobs
Rollover up to 1,000 credits

Start Power

Pay as you go: $0.15 per credit. No subscription required. Top up anytime.

up to 2-hour videos cache hits are free auto-refund on failure video deleted after processing

Credit cost per tool

quick_transcribe	1 credit
deep_analyze	5 credits
clip_context	3 credits (default) / 1 credit (quick mode)
batch_analyze	per video (−10% at 5+)

// setup

Connect in under a minute.

Contendeo is a remote MCP connector. Add it once in Claude's connector settings and use it in any conversation.

Open Claude (claude.ai or the Claude desktop app).
Click + → Connectors → Add custom connector.
Paste URL: https://contendeo.app/mcp/
Click Add → sign in with Google.
Start analyzing — paste any video URL and ask Claude to transcribe or analyze it.

▸ Works with Claude Pro, Max, Team, and Enterprise plans. Free plan is limited to 1 custom connector.

// faq

Questions, answered.

What video platforms are supported?

YouTube, Instagram Reels, Vimeo, Twitter/X, TikTok, and direct MP4 / webm URLs. yt-dlp covers 1,000+ sites in practice; the listed platforms are the ones we explicitly test and harden against bot detection.

How is this different from a transcript tool?

Contendeo doesn't just transcribe — it extracts visual context from keyframes, runs OCR on charts and dashboards, identifies entities (tokens, protocols, people), and synthesizes everything into structured intelligence. A pure transcript misses anything said on-screen.

What happens to my video data?

Videos are downloaded, processed in memory, and immediately deleted after processing. We never store video content. Only the analysis result is cached for 7 days, keyed by a hash of the URL, so repeat requests hit the cache instantly and cost zero credits.

Can I use it for crypto / trading content?

Yes. Contendeo ships with specialized vision prompts for financial charts, order books, protocol diagrams, and token metrics. Set focus to "crypto" on deep_analyze for optimized extraction — exact prices, support/resistance levels, and TVL numbers are pulled verbatim from the frame.

What if the analysis fails?

Credits are automatically refunded on any failure — download error, API timeout, invalid URL, anything. Cache hits never charge credits in the first place. Every deduct and refund is logged with the full audit trail.