MCP-Http-Client
MCP server for making HTTP requests with natural language
claude mcp add --transport stdio ferprieto-mcp-http-client npx -y @mcp/http-client
How to use
The MCP HTTP Client server lets you perform HTTP requests, GraphQL queries, and TCP/Telnet connections directly from AI assistants. It includes intelligent response formatting, automatic JSON pretty-printing, content-type auto-detection, and a built-in caching layer to speed up repeated requests. You can issue natural language style commands to craft requests, and the server will output structured results with status indicators, timing metrics, and response sizes, making it suitable for AI-driven workflows. The tool supports common content types (JSON, form-data, URL-encoded) and can handle GraphQL targets natively, returning parsed results and helpful metadata. Additionally, it exposes capabilities for performance monitoring and quick reuse of previously fetched data via the cache, enabling faster iteration during AI-assisted development.
How to install
Prerequisites:
- Node.js and npm installed for the npm installation path
- Optional: Homebrew for macOS/Linux package installation
- Optional: Java JDK and Gradle for building from source
Installation paths:
- Install via npm (recommended for quick setup)
npm install -g @mcp/http-client
- Install via Homebrew (macOS/Linux)
brew tap ferPrieto/mcp-http-client
brew install mcp-http-client
- Use GitHub Packages (Kotlin/JVM projects) in a Gradle project
repositories {
maven {
url = uri("https://maven.pkg.github.com/ferPrieto/MCP-Http-Client")
credentials {
username = project.findProperty("gpr.user") as String? ?: System.getenv("GITHUB_ACTOR")
password = project.findProperty("gpr.key") as String? ?: System.getenv("GITHUB_TOKEN")
}
}
}
dependencies {
implementation("ferprieto.mcp:httpclient:1.0.0")
}
- Build from source (Java/Kotlin project)
git clone https://github.com/ferPrieto/MCP-Http-Client.git
cd MCP-Http-Client
./gradlew clean build
This builds the JAR at build/libs/mcp-http-client-all.jar if you choose the JAR-based setup.
Additional notes
Tips and common considerations:
- If you install via npm, you can run the server with a configuration entry that uses the npx command as shown in the examples. For Homebrew installations, the config usually points directly to the binary (mcp-http-client).
- When using GitHub Packages (Kotlin/JVM), you must authenticate with a GitHub Personal Access Token (read:packages) to fetch the dependency.
- The MCP client configuration can be added to your MCP client config file (e.g., ~/.cursor/mcp.json). Example entries are shown in the README for npm, Homebrew, and JAR usage.
- Environment variables like GITHUB_ACTOR or GITHUB_TOKEN may be required for certain installation paths. Ensure these are set in your environment if you rely on GitHub Packages.
- For advanced workflows, consider enabling caching and monitoring options provided by the server to optimize repeated requests in AI-assisted sessions.
- If you plan to run the JAR directly, ensure you’ve built the project or downloaded the prebuilt jar and reference the proper path in the config.
Related MCP Servers
gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
ReActMCP
ReActMCP is a reactive MCP client that empowers AI assistants to instantly respond with real-time, Markdown-formatted web search insights powered by the Exa API.
mcp-bsl-platform-context
MCP сервер для AI-ассистентов (справка по синтаксису и объектной модели 1С:Предприятие)
furi
CLI & API for MCP management
biznagafest
MCP Servers en Málaga con salero
unity-editor
An MCP server and client for LLMs to interact with Unity Projects