About clypt
clypt is an MCP server that connects AI agents to Clypt’s podcast-processing API. It accepts podcast URLs and returns generated clips and related materials through an asynchronous job flow.
Key features
- 01Submit podcast URLs as jobs
- 02Retrieve job status and results
- 03List recent paginated jobs
- 04Return clips, trailers, notes, and transcripts
- 05Support live and sandbox API keys
Use cases
- 01Create clips from an audio or RSS podcast
- 02Process video and request a trailer
- 03Check completed jobs for transcripts and show notes
MCP support
Exposes three tools to MCP clients: submit_job, get_job, and list_jobs. Clients submit work, poll for completion, and retrieve clips and other output.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @useclypt/mcp-serverCLYPT_API_KEYSecretClypt API key. Get one at https://useclypt.com/developers. Use a clk_test_* sandbox key for free deterministic fixtures.CLYPT_BASE_URLOverride the Clypt API base URL. Defaults to https://useclypt.com.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
3Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| source | object | Yes | Where to fetch the source media from. |
| source.url | string | Yes | Public HTTPS URL of the media or RSS feed. |
| source.type | enum | Yes | Where the media lives. video_url = publicly fetchable MP4, audio_url = MP3/M4A, rss_feed_url = podcast RSS (most recent episode is picked), youtube_url = beta.video_url | audio_url | rss_feed_url | youtube_url |
| options | object | No | Optional job-level overrides. |
| options.caption_style | string | No | Optional caption preset override. Examples: 'bold-pop', 'yellow-pop'. Omit to use the org default. |
| options.include_trailer | boolean | No | Set true on video_url submissions to also produce a 60-90s vertical highlights MP4 alongside the clips. Audio sources can't produce trailers. |
| idempotency_key | string | No | Optional idempotency token (8-255 chars). Re-submitting the same body with the same key inside 24h returns the original job instead of creating a new one. |
Details
From the project README@useclypt/mcp-server
Model Context Protocol server for Clypt. Lets AI agents (Claude Desktop, Cursor, Claude Code, any MCP-aware client) submit a podcast URL and receive clips, an optional trailer, show notes, a guest-share link, and the transcript.
Pure shim over the public REST API at https://useclypt.com/api/v1 — three tools, no clever middleware.
Tools
| Tool | Wraps | Returns |
|---|---|---|
submit_job | POST /v1/jobs | { id, status: 'queued', ... } — kicks the pipeline. Wall-clock to terminal: ~2-5 min for audio/RSS sources, ~10-12 min for video + trailer. |
get_job | GET /v1/jobs/{id} | Current job state. When status='complete', output contains clips, optional trailer, guest_share_url, show_notes, transcript. When failed, error carries a code + message. |
list_jobs | GET /v1/jobs | Cursor-paginated list of the org's recent jobs. |
The flow is asynchronous: submit_job returns immediately with a queued id; the agent polls get_job until terminal. Once a webhook is registered against your org, job.completed and job.failed events fire on every terminal transition — register via the public API at POST /v1/webhooks (no MCP tool for this yet; coming in a later minor).
Try it
With the server configured in Claude Desktop, ask:
Use Clypt to clip this podcast and tell me when it's done: https://feeds.simplecast.com/abc123
Claude will call submit_job, get back a job id, poll get_job until terminal, and surface the clips + trailer + transcript inline. Wall-clock: ~2-5 min for audio/RSS, ~10-12 min for video + trailer.
Installation
npm install -g @useclypt/mcp-server
Or run without installing:
npx -y @useclypt/mcp-server
Configuration
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"clypt": {
"command": "npx",
"args": ["-y", "@useclypt/mcp-server"],
"env": {
"CLYPT_API_KEY": "clk_live_..."
}
}
}
}
Restart Claude Desktop. Then prompt: "Use Clypt to clip this podcast: ".
Cursor / Claude Code / other MCP hosts
Same recipe — the binary is mcp-server (or run without global install via npx -y @useclypt/mcp-server) and the only required env var is CLYPT_API_KEY.
Sandbox keys (free testing)
If your key starts with clk_test_ instead of clk_live_, every job returns a deterministic fixture instead of running the real pipeline. No transcription cost, no R2 storage cost, no Stripe charges. Useful for wiring up your agent before you commit to real submissions.
Fixture mapping:
source.type='video_url'(any URL) → success fixture with 3 clips + optional trailersource.type='audio_url'/rss_feed_url(URL without "fail") → success fixture- Any URL containing "fail" →
transcription_failederror fixture source.type='youtube_url'→youtube_ingestion_failederror fixture- Malformed URL →
invalid_source_urlvalidation error at submit
Get a sandbox key in seconds at useclypt.com/developers/signup — no credit card, no waiting list. Sandbox keys (prefix clk_test_) return deterministic fixtures so you can wire up your agent for free before swapping in a clk_live_ key.
Environment variables
| Variable | Required | Default | Purpose |
|---|---|---|---|
CLYPT_API_KEY | yes | — | Bearer token for the Clypt API. clk_live_* or clk_test_*. |
CLYPT_BASE_URL | no | https://useclypt.com | Override for staging or local development. Trailing slash is stripped. |
Development
npm install
npm run build
npm test # vitest unit tests with mocked fetch
npm run dev # tsc --watch
Smoke against the live API with the MCP inspector CLI:
npm run build
CLYPT_API_KEY=clk_test_xxx \
npx @modelcontextprotocol/inspector --cli node dist/index.js --method tools/list
Learn more
- API reference: useclypt.com/developers/docs
- Get a key: useclypt.com/developers/signup
- About Clypt: useclypt.com
License
MIT — see LICENSE.
Comments
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.