Fetch MCP Server

Developmentstdiov2026.1.26

Provides HTTP request capabilities through the Model Context Protocol. Enables AI agents to fetch web content, retrieve API responses, and download resources from URLs. Supports converting HTML to Markdown for easier consumption and can handle various content types including JSON, text, and binary data.

http fetch web api-client networking

连接

将此配置添加到 .claude/mcp.json

{
  "mcpServers": {
    "fetch": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetch"
      ]
    }
  }
}

工具 (1)

fetch

Fetch a URL and return its content. HTML is converted to Markdown by default for readability.

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "raw": {
      "type": "boolean",
      "description": "Return raw content without HTML-to-Markdown conversion"
    },
    "url": {
      "type": "string",
      "description": "URL to fetch"
    },
    "max_length": {
      "type": "integer",
      "description": "Maximum number of characters to return (default 5000)"
    },
    "start_index": {
      "type": "integer",
      "description": "Start content from this character index for pagination"
    }
  }
}

资源

此服务器未提供任何资源。

提示词

此服务器未提供任何提示词。

服务器信息

作者: Anthropic (@modelcontextprotocol)
代码仓库: https://github.com/modelcontextprotocol/servers
许可证: Apache-2.0
版本: 2026.1.26
星标: 86,206
最后更新: 2026年1月27日