# Watch Skill (MCP server)

> Watch Skill is an MCP server that adds cloud and DevOps tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Watch video and live sessions, keep timestamped evidence, and verify an agent's own work. It has 452 GitHub stars, is released under the MIT license and runs locally with uvx watch-skill.

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence, and answers did that actually work? with a deterministic contract rather than a model's opinion. Add it to the agent you already use over MCP.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/oxbshw/watch-skill |
| GitHub stars | 452 |
| License | MIT |
| Language | Python |
| Transport | stdio |
| Packages | pypi: watch-skill |
| Remote URL | none |
| Needs API key | no |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | Cloud & DevOps |
| Latest release | deepwatch-v0.1.4 (Sep 8, 2026) |
| Last commit | Sep 8, 2026 |
| MCP registry name | io.github.oxbshw/watch-skill |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "watch-skill": {
      "command": "uvx",
      "args": [
        "watch-skill"
      ]
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --transport stdio watch-skill -- uvx watch-skill
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "watch-skill": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "watch-skill"
      ]
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "watch-skill": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "watch-skill"
      ]
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Similar MCP servers

- [Worldmonitor](https://appsgit.com/mcp-servers/worldmonitor): Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface. (87,920 stars, AGPL-3.0)
- [Netdata](https://appsgit.com/mcp-servers/netdata): Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection. (80,817 stars, GPL-3.0, needs API key)
- [openstatus](https://appsgit.com/mcp-servers/openstatus): Manage monitors, status pages, incidents and maintenances in your openstatus workspace. (9,171 stars, AGPL-3.0, official)
- [MCP Server Cloudflare](https://appsgit.com/mcp-servers/mcp-server-cloudflare): Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. (4,360 stars, Apache-2.0, official, needs API key)
- [Dagu](https://appsgit.com/mcp-servers/dagu): Self-hostable workflow orchestrator for teams whose main work isn't orchestration. (4,289 stars, GPL-3.0)
- [Azure MCP Server](https://appsgit.com/mcp-servers/azure-mcp-server): All Azure MCP tools to create a seamless connection between AI agents and Azure services. (3,738 stars, MIT, official)

---

Canonical page: https://appsgit.com/mcp-servers/watch-skill
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed nightly.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.