This MCP server allows Claude Desktop (or any MCP client) to fetch web content and process images. It extracts web content as markdown, processes images with optimization, and provides flexible configuration options for how content is handled.
To use this tool with Claude Desktop, add the following to your Claude Desktop configuration file:
{
"tools": {
"imageFetch": {
"command": "npx",
"args": ["-y", "@kazuph/mcp-fetch"]
}
}
}
The configuration file is located at: ~/Library/Application Support/Claude/claude_desktop_config.json
You can easily access this through Claude Desktop:
For automated clipboard operations to work properly:
To fetch web content without images:
{
"url": "https://example.com"
}
To fetch web content and save images to your local system:
{
"url": "https://example.com",
"enableFetchImages": true,
"imageMaxCount": 3
}
Images will be saved to ~/Downloads/mcp-fetch/YYYY-MM-DD/
directory.
To fetch web content and encode images for AI display:
{
"url": "https://example.com",
"enableFetchImages": true,
"returnBase64": true,
"imageMaxCount": 3
}
To fetch additional images from the same content:
{
"url": "https://example.com",
"enableFetchImages": true,
"imageStartIndex": 3,
"imageMaxCount": 3
}
The following parameters can be used to customize the behavior:
url
(required): The URL to fetchmaxLength
(default: 20000): Maximum length of content to returnstartIndex
(default: 0): Starting position in contentimageStartIndex
(default: 0): Starting position for image collectionraw
(default: false): Return raw content instead of processed markdownimageMaxCount
(default: 3): Maximum number of images to process per requestimageMaxHeight
(default: 4000): Maximum height of merged imageimageMaxWidth
(default: 1000): Maximum width of merged imageimageQuality
(default: 80): JPEG quality (1-100)enableFetchImages
(default: false): Enable fetching and processing of imagessaveImages
(default: true): Save processed images to local filesreturnBase64
(default: false): Return base64 encoded images for AI displayignoreRobotsTxt
(default: false): Ignore robots.txt restrictionsTo add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "imageFetch" '{"command":"npx","args":["-y","@kazuph/mcp-fetch"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"imageFetch": {
"command": "npx",
"args": [
"-y",
"@kazuph/mcp-fetch"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"imageFetch": {
"command": "npx",
"args": [
"-y",
"@kazuph/mcp-fetch"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect