Media

screenshot - Claude MCP Skill

Take a screenshot of a URL or the current page. Use when the user asks to capture, screenshot, or photograph a web page or URL.

SEO Guide: Enhance your AI agent with the screenshot tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to take a screenshot of a url or the current page. use when the user asks to capture, screenshot, or ph... Download and configure this skill to unlock new capabilities for your AI workflow.

🌟71 stars • 43 forks
📥0 downloads

Documentation

SKILL.md
# /firefox-devtools-mcp:screenshot

Captures a screenshot of a URL or the current page and shows it to the user.

## Usage

```
/firefox-devtools-mcp:screenshot https://example.com   # Navigate then screenshot
/firefox-devtools-mcp:screenshot                       # Screenshot current page
/firefox-devtools-mcp:screenshot <uid>                 # Screenshot specific element
```

## Steps

1. Navigate if a URL was given: call `navigate_page`.
2. Take the screenshot using the method that matches your environment:

**In Cowork** (system prompt contains an outputs folder host path under "Shell access"):
- Call `screenshot_page saveTo="<host-outputs-path>/screenshot.png"` using the host path from the system prompt, not the container path.
- Load and call `present_files` with that same path so the user receives a clickable file card.

**In Claude.ai chat or Claude Desktop** (no outputs folder in system prompt):
- Call `screenshot_page` without `saveTo`.
- Your final response must include the actual image returned — not a description of it. The user cannot see tool call outputs, only what you include in your reply.

Signals

Avg rating0.0
Reviews0
Favorites0

Information

Repository
freema/firefox-devtools-mcp
Author
freema
Last Sync
7/8/2026
Repo Updated
7/8/2026
Created
7/3/2026

Reviews (0)

No reviews yet. Be the first to review this skill!

screenshot - Claude/MCP Skill for AI Agents | SkillAvatars | SkillAvatars