An MCP stdio server that exposes the `watch-cli` command as a single `watch` tool for MCP-capable agents. The tool takes a social video URL and optional frame count, then returns the JSON output produced by `watch-cli`.
From the registry: Hand any social video to your AI agent — frames + transcript bundled. MCP server for watch-cli.
$ curl -fsSL https://raw.githubusercontent.com/sonpiaz/watch-cli/main/install.sh | bashhttps://github.com/sonpiaz/watch-cliPlease install the `watch-cli` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js** — Node.js 18 or newer is required to run the MCP server via npm/npx.
- **Install watch CLI** — The MCP server shells out to the `watch` CLI, which must be installed and available on PATH. Run: `curl -fsSL https://raw.githubusercontent.com/sonpiaz/watch-cli/main/install.sh | bash` (https://github.com/sonpiaz/watch-cli)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@sonpiaz/watch-cli-mcp"]
Note: Prefer the on-demand npx install path. The server communicates over stdio, reading JSON-RPC from stdin, writing JSON-RPC to stdout, and logging to stderr.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.