About clipmaster-mcp
clipmaster-mcp exposes ClipMaster’s video clipping API to AI clients, covering URL-based YouTube ingestion through clip exports and scheduled posts.
Key features
- 01Import YouTube videos by URL
- 02Track video processing status
- 03Browse projects and generated clips
- 04Export clips and check export status
- 05Schedule posts to connected channels
Use cases
- 01Generate clips from a YouTube video
- 02Review clips and their AI metadata
- 03Render a clip with saved settings
- 04Schedule an export for publication
MCP support
An MCP server that exposes ClipMaster’s public REST API as tools for MCP clients. It uses an API key and does not access databases or internal services.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx clipmaster-mcpCLIPMASTER_API_KEYSecretClipMaster API key (cm_live_...), created in the ClipMaster app under Settings -> API access. Available on paid plans.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
12Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| url | string | Yes | |
| user_query | any | No | |
| orientation | string | No | |
| compilation_format | any | No |
Details
From the project READMEclipmaster-mcp
mcp-name: io.github.n0Sp00n/clipmaster-mcp
MCP (Model Context Protocol) server for ClipMaster — AI video clipping at clipmaster.app. It exposes the ClipMaster public API as tools, so Claude Desktop, Claude Code, and any MCP client can ingest videos, monitor processing, browse clips, trigger exports, and schedule posts.
- Talks ONLY to the public REST API (
https://api.clipmaster.app/api/v1) with the user's API key — no database access, no internal services. - Ingestion is URL-only by design (streaming a local file through an LLM tool call is impractical). Account management (keys, billing, OAuth connects) is excluded; the API rejects those routes for key auth anyway.
Requirements
- Python 3.10+
- A ClipMaster API key (paid plans): web app → Settings → API access
Install
From this repo checkout:
pipx install ./clipmaster-mcp
# or, without installing:
uvx --from ./clipmaster-mcp clipmaster-mcp
Configure
| Env var | Required | Meaning |
|---|---|---|
CLIPMASTER_API_KEY | yes* | Your cm_live_… API key |
CLIPMASTER_API_BASE | no | Override the API base URL (default https://api.clipmaster.app/api/v1) |
*Instead of the env var you can put the key in ~/.config/clipmaster/key —
this keeps it out of client config files and shell history:
mkdir -p ~/.config/clipmaster && printf '%s' 'cm_live_...' > ~/.config/clipmaster/key && chmod 600 ~/.config/clipmaster/key
The env var wins when both are set.
Claude Code
claude mcp add clipmaster -e CLIPMASTER_API_KEY=cm_live_... -- clipmaster-mcp
Claude Desktop
claude_desktop_config.json:
{
"mcpServers": {
"clipmaster": {
"command": "clipmaster-mcp",
"env": { "CLIPMASTER_API_KEY": "cm_live_..." }
}
}
}
Tools
| Tool | What it does |
|---|---|
ingest_youtube(url, orientation?, user_query?, compilation_format?) | Import a YouTube video, start clip generation |
get_status(project_id) | Processing progress / state |
list_projects() | The user's projects |
list_clips(project_id) | Generated clips with AI metadata |
get_clip(project_id, clip_id) | Full detail for one clip |
trigger_export(project_id, clip_id) | Render a clip with its saved settings (charges tokens) |
get_export_status(export_id) | Poll an export; completed → temporary download_url |
list_compilations(source_project_id?) / get_compilation(id) | Cross-project clip collections |
list_social_accounts() | Connected channels for scheduling |
schedule_post(...) | Schedule an export to publish (idempotent on retry) |
list_scheduled_posts(from_date, to_date) | Posting calendar range |
Development
python3 -m venv .venv && .venv/bin/pip install -e ./clipmaster-mcp pytest
.venv/bin/pytest clipmaster-mcp/tests -q
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.