MCP API Requester
Click on "Deploy 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., "@MCP API Requester GET https://jsonplaceholder.typicode.com/posts/1"
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.
MCP API Requester
A Model Context Protocol (MCP) server that enables LLMs to make arbitrary HTTP API requests (GET, POST, PUT, DELETE, etc.) with custom headers and bodies. Works with Claude Desktop and other MCP-compatible AI tools.
Features
π HTTP Operations: Make any HTTP request (GET, POST, PUT, DELETE, PATCH, etc.)
π§ Custom Configuration: Full control over headers, query parameters, and request body
π JSON Support: Native handling of JSON request and response bodies
π Robust Error Handling: Returns 4xx/5xx responses as structured data instead of failing, allowing the LLM to inspect errors
π Safe Execution: Useful for testing APIs, webhooks, and interacting with external services
Related MCP server: Web Request MCP Server
Installation
Using npx (Recommended)
No installation needed! Just configure Claude Desktop to use npx:
{
"mcpServers": {
"api-requester": {
"command": "npx",
"args": [
"-y",
"github:yryuu/mcp-api-requester"
]
}
}
}Local Installation
git clone <repository-url>
cd mcp-api-requester
npm install
npm run buildConfiguration
Claude Desktop
Edit your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the server configuration:
{
"mcpServers": {
"api-requester": {
"command": "node",
"args": ["/absolute/path/to/mcp-api-requester/dist/index.js"]
}
}
}Available Tools
make_request
Make an arbitrary HTTP request.
Parameters:
url(string): The full URL to make the request to.method(string): HTTP method (GET, POST, PUT, DELETE, PATCH, etc.). Defaults to GET.headers(object, optional): Key-value pairs of HTTP headers.params(object, optional): Key-value pairs of URL query parameters.cookies(object, optional): Key-value pairs of cookies to be included in the request.body(object/string, optional): The request body. Content-Type header should match this body.
Example (GET):
Make a GET request to https://api.example.com/users?id=123Example (POST):
POST to https://api.example.com/data with content-type application/json and body {"key": "value"}Example (Cookies):
Make a GET request to https://api.example.com/profile with cookies {"session": "abc", "theme": "dark"}Development
Setup
cd mcp-api-requester
npm installBuild
npm run buildTesting
Run the included manual test script:
npm testNote: uses
tsxto run the TypeScript test file directly.
Debugging
Use the MCP Inspector to test the server:
npx @modelcontextprotocol/inspector node dist/index.jsSecurity
Warning: This tool enables the LLM to make requests to any URL you provide or it discovers.
Ensure you only use this in a trusted environment.
Be cautious when asking the LLM to interact with sensitive APIs or internal services.
License
MIT
Author
yryuu
Available Tools
1 toolmake_requestA
Make an arbitrary HTTP request (GET, POST, PUT, DELETE, etc.) with custom headers and body. Returns the status, headers, and body of the response.
Inputs: url (required), body, method, params, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion or overlapping purposes. The single tool's purpose is clearly defined as making arbitrary HTTP requests.
With a single tool named 'make_request', the naming follows a clear verb_noun pattern. There are no other tools to create inconsistency.
The server has just one tool, which is slightly below the typical 3-15 range, but for a focused HTTP request utility this is reasonable. The tool is general-purpose and well-suited to the server's stated purpose.
The single tool covers the full scope of making HTTP requests: all methods, custom headers, body, and returns status, headers, and body. There are no obvious gaps in the server's intended functionality.
Maintenance
Related MCP Connectors
Nifty's MCP server β exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Related MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol server that enables AI assistants to make HTTP requests (GET, POST, PUT, DELETE) to external APIs through standardized MCP tools.42MIT
- AlicenseAqualityDmaintenanceA TypeScript-based MCP server that enables AI assistants to execute HTTP requests with full control over methods, headers, and body content. It facilitates seamless interaction with web APIs and endpoints through a versatile tool that handles automatic JSON formatting and response truncation.1MIT
- AlicenseNot gradedqualityDmaintenanceA powerful MCP server for making HTTP requests, GraphQL queries, and TCP/Telnet connections from AI assistants.7MIT
- FlicenseAqualityDmaintenanceUniversal HTTP client tool for LLM agents. Enables Claude and other MCP-compatible agents to perform GET, POST, PUT, DELETE, and other HTTP requests to any URL, including localhost and internal network addresses.2-