Importly MCP

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/importly-io-importly-mcp

About

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

7 read · 1 write · 0 delete · 1 not yet classified

Secrets

1 (API keys, tokens or passwords)

Install scripts

Not scanned yet

Runs as

Node.js package

Tools (9)

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

• check_balance

  Check the remaining Importly credit balance for the configured API key. Use this to diagnose failed jobs (insufficient credits) or as a pre-flight check before large imports/transcriptions.

• check_basic_metadata

  Check the status of a get_basic_metadata job. Returns title, duration, and thumbnail once completed.

• check_import

  Check the status of an import_media job. Returns the media download URL (and transcript, if requested) once the job completes.

• check_metadata

  Check the status of a get_metadata job. Returns the full metadata object once completed.

• check_transcription

  Check the status of a transcribe_media job. Returns the transcript text and timestamped segments once completed.

• get_basic_metadata

  Fast-path metadata for a video/audio URL: title, duration, and thumbnail only. Cheaper and quicker than get_metadata — use this to identify or validate a media URL before importing or transcribing it. Async: poll check_basic_metadata with the returned jobId.

• get_metadata

  Extract full metadata for a video/audio URL (title, description, duration, uploader, formats, thumbnails, view counts) without downloading the media. Works on YouTube, TikTok, X, and 1000+ sites — no yt-dlp to run yourself. Async: poll check_metadata with the returned jobId. For just title/duration/thumbnail, prefer the faster get_basic_metadata.

• import_media

  Download the video/audio at any URL (YouTube, TikTok, X, and 1000+ sites) to hosted storage and get back a direct download link. Importly runs yt-dlp, rotating residential proxies, and ffmpeg server-side — no local tooling needed. Async: returns a jobId immediately; poll check_import for the result. Optionally also produce a transcript in the same job with includeTranscript.

• transcribe_media

  Transcribe the audio of any video/audio URL (YouTube, TikTok, podcasts, and 1000+ sites) to text with timestamped segments. Importly handles the download, audio extraction, and speech-to-text server-side — no yt-dlp or ffmpeg needed. Async: returns a jobId immediately; poll check_transcription for the transcript. Costs scale with media length; set maxCostDollars to cap spend on long media.

Signals

Stars

0

Forks

0

Open issues

1

Last commit

Jul 20, 2026 (3 months ago)

Last release

Jul 20, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.importly/importly-mcp

Version

0.1.0

Auth

API key

Packages

npm importly-mcp

License

MIT

Repository

github.com/yyildiz/importly-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql