mcpField
U
uploadcheck

uploadcheck

Local
uploadcheck.appMedia & Design0Updated 14w ago

About uploadcheck

UploadCheck is a media quality-check service for agents, production pipelines, and editors. It returns a PASS, WATCH, or BLOCK verdict with timestamped issues and repair guidance for video and audio files.

Key features

  1. 01Run more than 40 media checks
  2. 02Flag picture, audio, sync, and text issues
  3. 03Return verdicts with timestamped evidence
  4. 04Generate editor marker CSV files
  5. 05Check local files and video URLs

Use cases

  1. 01Inspect a rendered video before publishing
  2. 02Find audio dropouts in a podcast
  3. 03Locate cropped captions in a short-form clip
  4. 04Send flagged timestamps to an editing timeline

MCP support

The MCP server exposes tools to estimate and run checks, retrieve job status and reports, and generate artifacts such as editor marker CSV files. It uses the hosted UploadCheck API; checks run server-side.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"app-uploadcheck-uploadcheck": {
"command": "npx",
"args": [
"-y",
"@drantoniou/uploadcheck-mcp"
],
"env": {
"UPLOADCHECK_API_BASE_URL": "<UPLOADCHECK_API_BASE_URL>",
"UPLOADCHECK_API_KEY": "<UPLOADCHECK_API_KEY>"
}
}
}
}
Run commandnpx -y @drantoniou/uploadcheck-mcp
Environment variables to set
UPLOADCHECK_API_BASE_URLUploadCheck API base URL
UPLOADCHECK_API_KEYSecretWorkspace API key from your UploadCheck setup email (get one at https://uploadcheck.app/checkout/)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@drantoniou/uploadcheck-mcp0.1.1

Tools

9

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
checksstringNo
minutesnumberNo
plan_idstringNo
profilestringNo
cost_guardrailenumNodowngrade | block | off
duration_secondsnumberNo
included_minutesnumberNo
plan_price_centsnumberNo
ai_review_secondsnumberNo

Details

From the project README

🎬 UploadCheck MCP

The quality gate between your AI and "publish".

Your agent can generate video. It can't tell you the audio cut out at 0:08, a frame froze at the stitch seam, or the captions are cropped. UploadCheck can — and hands back the exact timestamps to fix.

npm License: MIT For: Claude Code · Cursor · Codex Free tier

For anyone whose agent, pipeline, or editor produces media that ships to real people — AI-video pipelines, Shorts/Reels, podcasts, client deliverables.


The problem

An agent that writes code can run the tests. An agent that renders a video has no idea whether it's broken.

So the broken export ships: silence where narration should be, a frozen frame where two clips were stitched, lips out of sync, captions clipped by the platform UI, loudness well off target. Somebody notices in the comments.

UploadCheck is the check your agent calls before it publishes. Point it at the finished file. It returns PASS, WATCH, or BLOCK with per-flag timestamps and machine-actionable fixes — so the agent repairs only the flagged span and re-checks, instead of guessing or shipping.

Install

npx -y @drantoniou/uploadcheck-mcp
Claude Code
claude mcp add --env UPLOADCHECK_API_BASE_URL=https://api.uploadcheck.app \
  --env UPLOADCHECK_API_KEY=YOUR_KEY \
  --transport stdio --scope user uploadcheck -- npx -y @drantoniou/uploadcheck-mcp
Cursor / Claude Desktop (mcp.json)
{
  "mcpServers": {
    "uploadcheck": {
      "command": "npx",
      "args": ["-y", "@drantoniou/uploadcheck-mcp"],
      "env": {
        "UPLOADCHECK_API_BASE_URL": "https://api.uploadcheck.app",
        "UPLOADCHECK_API_KEY": "YOUR_KEY"
      }
    }
  }
}
Codex
codex mcp add uploadcheck \
  --env UPLOADCHECK_API_BASE_URL=https://api.uploadcheck.app \
  --env UPLOADCHECK_API_KEY=YOUR_KEY \
  -- npx -y @drantoniou/uploadcheck-mcp

Get a free key at uploadcheck.app — 40+ gates, 200 checked minutes/month, no card. Machine-readable install snippets for every client live in mcp-install.json.

Keep your key private. It's a secret bearer token tied to your plan minutes. Put it in your personal MCP config — never in a committed file, a shared prompt, or a report.

Use it

Once installed, just ask:

check ./final-cut.mp4 before I upload

The agent calls qc_run_local_file, polls qc_get_job, then reads qc_get_report and shows you the flags with timestamps.

What it checks

40+ automated gates run on every check, including:

Picturefrozen/looped frames, black frames, canvas fit & pillarboxing, temporal warping, flicker, interlace combing
Audiodead air, clipping, loudness (LUFS) & true peak, loudness range, channel balance, mains hum, dropouts
Sync & textlip/audio drift, caption safe-area, text contrast, cropped or overlapping text
Deliveryresolution/codec/frame-rate spec, Shorts/Reels format

Paid plans add AI "oracle" gates — garbled speech, duplicated faces in AI crowds, narration match.

What it doesn't do: it doesn't tell you whether a clip was AI-generated. It assumes it might be, and checks whether it's clean enough to publish.

Tools

ToolWhat it does
qc_estimate_costEstimate checked minutes and effective gates before running
qc_run_local_fileCheck a local export (reads the file, sends it to the hosted API)
qc_run_videoCheck a YouTube URL, signed URL, upload id, or base64 payload
qc_get_jobPoll status, progress, verdict, metered minutes
qc_get_reportThe finished report: verdict + timestamped flags + evidence
qc_get_eventsLifecycle events, so the agent can explain what ran
qc_get_artifactsList generated report artifacts
qc_get_marker_csvEditor marker CSV (drop flags straight into your NLE timeline)
qc_create_upload_urlSigned upload URL for larger files

Pass idempotency_key to qc_run_video when an agent might retry the same asset — the API returns the existing job instead of duplicating the run.

Use profile when you know the media type but don't want to hand-pick gates: auto, shorts, audio, thumbnail, generic_creator_video, and named delivery targets like youtube_shorts, podcast_delivery, broadcast_r128, ai_render_gate. Explicit checks always win.

Environment

export UPLOADCHECK_API_BASE_URL="https://api.uploadcheck.app"
export UPLOADCHECK_API_KEY="<workspace_api_key>"

This package is a thin MCP client over the hosted UploadCheck API — checks run server-side, not on your machine. Small and medium local files can be sent inline (base64) without durable storage; use signed upload URLs for large ones.

Links

License

MIT — see LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.