Allows installation of the Fetch API MCP server through npm package management, making it accessible as a global command-line utility.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Fetch API MCP Serverfetch https://api.github.com/repos/glama-ai/mcp with headers Authorization: Bearer token123"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Fetch API MCP 服务器
这是一个基于MCP（Model Context Protocol）的API请求服务器，可以发送各种HTTP请求并返回结果。
功能
支持多种HTTP方法（GET, POST, PUT, DELETE等）
支持自定义请求头
支持表单数据提交
支持JSON数据提交
支持Cookie设置
自动处理不同类型的响应（JSON, 文本, 二进制）
Related MCP server: Better Fetch
Cursor安装
npm 安装
npm install -g fetch-api-mcp打开 cursor mcp 配置，添加配置项：
"fetch-api": {
"command": "mcp-server-fetch-api"
}开发安装
npm install调试
启动服务器
npm start或者直接运行：
node src/index.js参数说明
MCP服务器接受以下参数：
url: 请求的URL（必填）method: 请求方法，默认为GETheaders: 请求头，对象格式formData: 表单数据，对象格式jsonData: JSON数据，对象格式cookies: Cookie数据，对象格式
返回数据
服务器返回以下数据：
status: HTTP状态码statusText: HTTP状态文本headers: 响应头data: 响应数据（会根据Content-Type自动解析为JSON、文本或Base64编码的二进制数据）
示例
发送GET请求
{
"url": "https://api.example.com/data",
"method": "GET",
"headers": {
"User-Agent": "MCP-Fetch-API/1.0"
}
}发送POST请求（JSON数据）
{
"url": "https://api.example.com/submit",
"method": "POST",
"headers": {
"User-Agent": "MCP-Fetch-API/1.0"
},
"jsonData": {
"name": "测试用户",
"email": "test@example.com"
}
}发送POST请求（表单数据）
{
"url": "https://api.example.com/form",
"method": "POST",
"formData": {
"username": "testuser",
"password": "password123"
}
}带Cookie的请求
{
"url": "https://api.example.com/profile",
"method": "GET",
"cookies": {
"session": "abc123",
"user_id": "12345"
}
}Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.