Curl MCP - Natural Language Curl Commander
LocalAbout Curl MCP - Natural Language Curl Commander
Curl MCP is an MCP server that turns English or Spanish instructions into curl requests. It is for users who want to make HTTP requests through natural language, with support for headers, authentication, submitted data, file uploads, and common request options.
Key features
- 01Convert English and Spanish instructions into requests
- 02Read response headers or raw responses
- 03Send authentication details and request data
- 04Upload files and set request options
Use cases
- 01Inspect website headers or raw content
- 02Send authenticated requests to an API
- 03Submit form data or upload files
- 04Make requests through a proxy or with a timeout
MCP support
The MCP server accepts natural language commands from MCP clients and executes the corresponding curl requests.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMECurl MCP - Natural Language Curl Commander
Execute curl commands using natural language in English and Spanish.
Prerequisites
- Python 3.13 or higher
- curl (usually pre-installed on Linux)
- Git
Installation
- Clone the repository:
git clone https://github.com/MartinPSDev/curl-mcp.git
cd curl-mcp
- Create and activate a virtual environment:
python3 -m venv .env
source .env/bin/activate
- Install dependencies:
pip install -r requirements.txt
- Start the MCP server:
python3 main.py
Configuration
Add this to your MCP settings:
{
"mcpServers": {
"curl-mcp": {
"command": "/usr/bin/python3",
"args": [
"/path/to/your/curl-mcp/main.py"
],
"env": {
"PYTHONPATH": "/path/to/your/curl-mcp/.env/lib/python3.11/site-packages"
}
}
}
}
Note: Replace /path/to/your/curl-mcp with the actual path where you cloned the repository.
Usage
- Start the MCP server:
python3 main.py
- The server can now receive natural language commands in English or Spanish. Here are some examples:
Basic Examples:
- "Get headers from https://example.com"
- "Show raw response from https://api.example.com"
- "Download https://example.com and save as page.html"
Advanced Examples:
-
Headers and Authentication:
- "Make a request to https://api.example.com with header Authorization: Bearer mytoken"
- "Get https://api.example.com using basic auth user:password"
-
Data Handling:
- "POST to https://api.example.com/users with data name=John and age=25"
- "Send form data to https://upload.example.com with file image.jpg"
- "POST urlencoded data user=test+name to https://api.example.com"
-
Security and Options:
- "Get https://example.com ignoring SSL verification"
- "Request https://api.example.com with timeout 30 seconds"
- "Get https://example.com through proxy localhost:8080"
-
User Agents:
- "Get https://example.com as Chrome"
- "Request https://mobile.example.com as iPhone"
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.