The MCP-URL2SNAP is a lightweight Model Context Protocol (MCP) server designed to enable AI models to capture screenshots of any specified URL and return the access URL for the captured image. This tool simplifies the process of generating and sharing webpage snapshots, making it ideal for integrating visual capture capabilities into AI applications like Claude Desktop or automation workflows.
MCP is a standardized protocol that streamlines communication between AI models and external systems. It acts as a universal language, allowing different AI agents, tools, and services to interact seamlessly.
MCP follows a client-server architecture, enabling efficient communication between AI models and external services.
Click the image below to watch a video demo of the MCP Email Verify tool in action:
git clone https://github.com/Abhi5h3k/MCP-URL2SNAP.git
cd MCP-URL2SNAP
If you don’t have UV installed, use the following commands:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Verify the installation:
uv --version
Create a virtual environment using UV:
uv venv
Activate the virtual environment:
- Windows:
.venv\Scripts\activate
Install the required dependencies from pyproject.toml
using UV:
uv install
Create a .env
file in the root directory and add your AbstractAPI key:
ABSTRACT_API_KEY=your_api_key_here
Start the MCP server:
uv run server.py
Update the claude_desktop_config.json
file to include your MCP server:
{
"mcpServers": {
"verify_mail": {
"command": "uv",
"args": [
"--directory",
"C:\\ABSOLUTE\\PATH\\TO\\MCP-Email-Verify",
"run",
"server.py"
],
"env": {
"ABSTRACT_API_KEY": "YOUR_API_KEY"
}
}
}
}
Restart Claude Desktop to detect the new tool.
Use prompts like:
"can you show me the screenshot of https://github.com/Abhi5h3k"
This project uses black
and isort
for code formatting and import sorting.
uv add black isort --dev
black .
isort .
pre-commit install
pre-commit run --all-files
Demo MCP tool to capture URL screenshots.