watch-skill
Level ALocalGive AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.
Installation
MCP client config (paste into mcp.json)
{
"mcpServers": {
"watch-skill": {
"command": "npx",
"args": [
"watch-skill"
]
}
}
}Agent install prompt
Copy and paste into Cursor / Claude / other agents to install this MCP for you
Please read this MCP repository and install it into my current environment:
https://github.com/oxbshw/watch-skill
Known working client config (can write into mcp.json):
{
"mcpServers": {
"watch-skill": {
"command": "npx",
"args": [
"watch-skill"
]
}
}
}
Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.
Related servers
LLM-Agents-Ecosystem-HandbookOne-stop handbook for building, deploying, and understanding LLM agents with 60+Agent-SpanThe Web Access Gateway for AI Agents — 52 channels, 92 MCP tools, 9 SDKs, self-hworldmonitorReal-time global intelligence dashboard. AI-powered news aggregation, geopoliticdeer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creatruflo🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinateheadroomCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20