The Fetch MCP Server enables language models to retrieve and process web content. It converts HTML pages to markdown for easier consumption, and allows reading lengthy webpages in chunks by supporting start index specification.
There are multiple ways to install and run the Fetch MCP Server, depending on your preferences and system setup.
Installing Node.js is optional but recommended for more robust HTML simplification.
When using uv
, you don't need a specific installation. You can use uvx
to run the server directly:
uvx mcp-server-fetch
Alternatively, install via pip:
pip install mcp-server-fetch
After installation, run it as:
python -m mcp_server_fetch
Add the server configuration to your Claude settings based 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"]
}
}
For manual VS Code installation, add the appropriate configuration to your User Settings (JSON) file or to .vscode/mcp.json
in your workspace:
{
"mcp": {
"servers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
}
}
{
"mcp": {
"servers": {
"fetch": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/fetch"]
}
}
}
}
By default, the server obeys robots.txt for model-initiated requests but not for user-initiated requests. To disable this behavior, add --ignore-robots-txt
to the args
list.
The server uses different user-agents depending on whether the request came from the model or was user-initiated. You can customize this by adding --user-agent=YourUserAgent
to the args
list.
Configure a proxy by adding the --proxy-url
argument to your configuration.
The Fetch MCP Server provides the following tool:
The main tool retrieves and processes web content:
fetch
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)For debugging with the MCP inspector:
npx @modelcontextprotocol/inspector uvx mcp-server-fetch
Or for a specific installation directory:
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.