The official Fetch MCP server enables AI agents to retrieve content from any URL.
uvx mcp-server-fetch
{
"mcpServers": {
"fetch": {
"args": [
"mcp-server-fetch"
],
"command": "uvx"
}
}
}Fetch a URL and return as Markdown
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string"
},
"method": {
"type": "string"
}
}
}// Input
{
"url": "https://example.com"
}// Output
{
"status": 200,
"content": "# Example Domain"
}Fetch URL and return raw response
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string"
}
}
}// Input
{
"url": "https://api.example.com/data.json"
}// Output
{
"content": "{}",
"mimeType": "application/json"
}The official Fetch MCP server enables AI agents to retrieve content from any URL.
Fetch provides 2 tools including fetch, fetch_raw.
Yes, Fetch is completely free to use with no usage limits on the free tier.
You can install Fetch using the following command: uvx mcp-server-fetch. After installation, add the provided config snippet to your Claude Desktop or Cursor configuration.
Fetch is listed under the Data & Analytics category in the AgentForge MCP registry.
Fetch has a current uptime of 99.92% with an average response time of 280ms.
To connect Fetch, click the "Connect Agent" button on this page to get the configuration snippet. Add it to your MCP client (Claude Desktop, Cursor, or any MCP-compatible tool). Your AI agent will then have access to all of Fetch's tools via the Model Context Protocol.