The Fetch MCP Server provides web content fetching capabilities for LLMs, allowing them to retrieve and process content from web pages by converting HTML to markdown for easier consumption. It enables models to read webpages in chunks by specifying a start index, making it possible to process long documents efficiently.
When using uv
, no specific installation is needed. 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 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:
Using uvx:
"mcpServers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
Using docker:
"mcpServers": {
"fetch": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/fetch"]
}
}
Using pip installation:
"mcpServers": {
"fetch": {
"command": "python",
"args": ["-m", "mcp_server_fetch"]
}
}
For manual installation, add the appropriate JSON block to your User Settings (JSON) file in VS Code:
Using uvx:
{
"mcp": {
"servers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
}
}
Using Docker:
{
"mcp": {
"servers": {
"fetch": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/fetch"]
}
}
}
}
You can also add this configuration to .vscode/mcp.json
in your workspace to share it with others.
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 default user-agent can be customized by adding --user-agent=YourUserAgent
to the args
list.
Configure a proxy by adding the --proxy-url
argument with your proxy URL.
The fetch
tool retrieves web content and converts it to markdown:
Required parameters:
url
(string): URL to fetchOptional parameters:
max_length
(integer): Maximum number of characters to return (default: 5000)start_index
(integer): Start content from this character index (default: 0)raw
(boolean): Get raw content without markdown conversion (default: false)Use the MCP inspector to debug the server:
npx @modelcontextprotocol/inspector uvx mcp-server-fetch
For specific installations:
cd path/to/servers/src/fetch
npx @modelcontextprotocol/inspector uv run mcp-server-fetch
Exercise caution when using this MCP server as it can access local/internal IP addresses, which may present a security risk. Ensure it doesn't expose sensitive data.
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.