This server automates HTTP/HTTPS API requests with JSON response validation and proxy support.
Send HTTP requests using GET, POST, PUT, DELETE, PATCH, HEAD, and OPTIONS methods
Set custom headers and request bodies (raw text or JSON string) for API calls
Upload files via multipart/form-data, supporting form fields (strings, numbers, booleans) and local files with configurable fieldName, filePath, filename, and contentType
Configure proxy servers via a proxy parameter or environment variables (HTTP_PROXY/HTTPS_PROXY/NO_PROXY), with the parameter taking precedence
Receive structured responses including parsed JSON data, status code, status text, and response headers
Handle errors gracefully with descriptive messages when requests fail or responses are not valid JSON
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., "@API Request MCP Server GET https://api.github.com/users/octocat/repos"
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.
一个用于自动发送 HTTP 请求并验证 JSON 响应的 MCP (Model Context Protocol) 服务器。支持多种 HTTP 方法、代理配置，以及 multipart/form-data 文件上传。
自动发送 GET、POST、PUT、DELETE、PATCH、HEAD、OPTIONS 请求
支持 HTTP 和 HTTPS
支持 HTTP/HTTPS 代理
自动校验响应是否为 JSON
支持原始文本请求体
支持 multipart/form-data
支持普通表单字段和本地文件同时上传
Related MCP server: cURL MCP Server
git clone https://github.com/your-username/api-request-server.git
cd api-request-server
npm install
npm run buildHTTP_PROXY=http://127.0.0.1:8080
HTTPS_PROXY=http://127.0.0.1:8080
NO_PROXY=localhost,127.0.0.1,.localHTTP_PROXY: HTTP 请求代理
HTTPS_PROXY: HTTPS 请求代理
NO_PROXY: 不走代理的主机列表
配置文件位置：项目根目录 .claude/mcp.json
{
"mcpServers": {
"api-request-server": {
"command": "node",
"args": [
"./api-request-server/build/index.js"
]
}
}
}如果你是直接在本仓库本地开发和调试，推荐使用绝对路径或与你当前项目结构一致的相对路径，并在修改后重启客户端以重新加载 MCP 配置。
Windows 配置文件位置：
%APPDATA%\\Code\\User\\globalStorage\\saoudrizwan.claude-dev\\settings\\cline_mcp_settings.json
{
"mcpServers": {
"api-request-server": {
"autoApprove": [
"send_api_request"
],
"disabled": false,
"timeout": 60,
"type": "stdio",
"command": "node",
"args": [
"C:\\path\\to\\api-request-server\\build\\index.js"
]
}
}
}本地开发时，也可以直接改成你自己的实际路径，例如：
{
"mcpServers": {
"api-request-server": {
"autoApprove": [
"send_api_request"
],
"disabled": false,
"timeout": 60,
"type": "stdio",
"command": "node",
"args": [
"C:\\Users\\gml\\Documents\\Cline\\MCP\\api-request-server\\build\\index.js"
]
}
}
}send_api_request({
"url": "https://api.example.com/data"
})send_api_request({
"url": "https://api.example.com/submit",
"method": "POST",
"headers": {
"Content-Type": "application/json",
"Authorization": "Bearer your-token"
},
"body": "{\"key\": \"value\"}"
})send_api_request({
"url": "https://api.example.com/data",
"proxy": "http://proxy-server:8080"
})send_api_request({
"url": "https://api.example.com/upload",
"method": "POST",
"headers": {
"Authorization": "Bearer your-token"
},
"formFields": {
"folder": "invoices",
"public": true,
"userId": 123
},
"files": [
{
"fieldName": "file",
"filePath": "C:\\data\\invoice.pdf",
"contentType": "application/pdf"
},
{
"fieldName": "attachment",
"filePath": "C:\\data\\note.txt",
"filename": "note.txt",
"contentType": "text/plain"
}
]
})send_api_request参数 | 类型 | 必需 | 说明 |
| string | 是 | 请求 URL，支持 |
| string | 否 | HTTP 方法，默认 |
| object | 否 | 请求头，键值对形式 |
| string | 否 | 原始请求体，适用于 JSON 或其他文本载荷 |
| object | 否 |
|
| array | 否 | 上传文件列表，每项为 |
| string | 否 | 代理地址，格式如 |
约束：
body 不能和 formFields、files 同时使用
files[].filePath 必须是本地真实存在的文件路径
上传文件时会自动生成 multipart/form-data 请求头
成功时返回：
{
"data": {
"key": "value"
},
"status": 200,
"statusText": "OK",
"headers": {
"content-type": "application/json"
}
}失败时返回：
{
"content": [
{
"type": "text",
"text": "Request failed: ..."
}
],
"isError": true
}proxy 参数
环境变量 HTTP_PROXY / HTTPS_PROXY
NO_PROXY 命中时不使用代理
当前实现要求响应可解析为 JSON，否则返回错误
目前仅支持 HTTP 和 HTTPS 代理
.env 不应提交到版本控制系统
npm install
npm run build
npm run watch
npm start本项目采用 MIT 许可证，详见 LICENSE。
发送API请求并返回JSON响应，支持多种协议和代理
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | 请求的URL，支持http和https协议 | |
| method | No | HTTP方法，如GET, POST, PUT, DELETE等 | GET |
| headers | No | 请求头对象，键值对 | |
| body | No | 请求体内容，对于POST等方法 | |
| proxy | No | 代理服务器地址，格式如 http://proxy.example.com:8080 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions returning JSON responses and supporting multiple protocols/proxies, but doesn't disclose critical behaviors like error handling, timeout settings, authentication requirements, rate limits, or what happens with non-JSON responses. For a general-purpose API tool, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Chinese that conveys the core functionality without waste. It's appropriately sized and front-loaded with the main purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a general API request tool with 5 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain return values, error conditions, or behavioral constraints. The agent lacks sufficient context to use this tool effectively beyond basic parameter filling.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all 5 parameters. The description adds no additional parameter semantics beyond mentioning protocol and proxy support, which is already implied by the schema. Baseline 3 is appropriate when the schema does all the work.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: '发送API请求并返回JSON响应' (send API request and return JSON response). It specifies the action (send request) and outcome (return JSON response), and mentions support for multiple protocols and proxies. However, it doesn't differentiate from siblings since there are none, so it's not a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It mentions support for multiple protocols and proxies, but doesn't specify use cases, prerequisites, or limitations. With no siblings, this is less critical, but the description lacks any usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0send_api_requestWith only one tool, there is no possibility of confusion or overlap with other tools, making disambiguation perfect. The tool has a clear and distinct purpose of sending API requests, so an agent cannot misselect between non-existent alternatives.
The single tool name 'send_api_request' follows a consistent verb_noun pattern, and with no other tools to compare, there is no inconsistency. The naming is clear and predictable for the server's scope.
A single tool is too few for a server named 'API Request MCP Server', which implies a broader scope for handling API interactions. This minimal set feels thin and incomplete for the apparent purpose, as it lacks operations like request configuration, error handling, or batch processing.
The tool surface is severely incomplete for an API request server. While 'send_api_request' covers the core action, there are obvious gaps such as no tools for managing request headers, authentication, retries, or parsing responses beyond JSON. This will likely cause agent failures in complex API workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.
AI-callable tools for API mocking, testing, monitoring, security, and automation.
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client. Air Pipe MCP token as a bearer credential, e.g. 'Authorization: Bearer <token>'. Create one at https://app.airpipe.io/
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Nicolas-One/api-request-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
