The Fetch MCP Server provides web content fetching capabilities for Large Language Models. It allows models to retrieve and process content from web pages by converting HTML to markdown, making it easier to consume. The server can fetch content in chunks, allowing models to read webpages incrementally until they find needed information.
When using uv
, no specific installation is needed. You can use uvx
to directly run the server:
uvx mcp-server-fetch
Install the server via pip:
pip install mcp-server-fetch
After installation, run it as a script:
python -m mcp_server_fetch
Installing Node.js is optional but recommended as it enables a more robust HTML simplifier.
Add one of the following configurations to your Claude settings, depending on your installation method:
"mcpServers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
"mcpServers": {
"fetch": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/fetch"]
}
}
"mcpServers": {
"fetch": {
"command": "python",
"args": ["-m", "mcp_server_fetch"]
}
}
By default, the server obeys a website's robots.txt file for model-initiated requests but not for user-initiated requests. To disable this behavior, add:
--ignore-robots-txt
to the args
list in your configuration.
The default user-agent varies based on whether the request came from the model or user. You can customize this by adding:
--user-agent=YourUserAgent
to the args
list in your configuration.
Configure the server to use a proxy by adding:
--proxy-url=YourProxyURL
to the args
list.
The server provides the following tool:
Fetches a URL and extracts its contents as markdown.
Arguments:
url
(string, required): URL to fetchmax_length
(integer, optional): Maximum number of characters to return (default: 5000)start_index
(integer, optional): Start content from this character index (default: 0)raw
(boolean, optional): Get raw content without markdown conversion (default: false)Use the MCP inspector to debug the server:
npx @modelcontextprotocol/inspector uvx mcp-server-fetch
Or if you're working with a local installation:
cd path/to/servers/src/fetch
npx @modelcontextprotocol/inspector uv run mcp-server-fetch
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 > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.