Curl MCP Server
A Model Context Protocol server that provides secure curl command execution capabilities, allowing AI assistants to make HTTP requests with configurable parameters and built-in security protections.
README
Curl MCP Server
A Model Context Protocol (MCP) server that provides secure curl command execution capabilities through terminal shell integration.
Features
- GET Requests: Execute HTTP GET requests with custom headers
- POST Requests: Send POST data with configurable content types
- Custom Commands: Execute custom curl commands with safety restrictions
- File Downloads: Download files and get metadata
- Security: Built-in protections against dangerous operations
- Timeouts: Configurable request timeouts (max 30 seconds)
- Output Limits: Protection against excessive output size
Installation
# Clone or create the project directory
mkdir curl-mcp-server
cd curl-mcp-server
# Install dependencies
npm install @modelcontextprotocol/sdk
npm install -D typescript @types/node tsx
# Create src directory and add the TypeScript code
mkdir src
# Place the server code in src/index.ts
# Build the project
npm run build
Prerequisites
- Node.js 18+
curlcommand available in PATH- TypeScript compiler
Available Tools
1. curl_get
Execute HTTP GET requests.
Parameters:
url(required): The URL to requestheaders(optional): Array of headers in "Key: Value" formattimeout(optional): Timeout in seconds (default: 10, max: 30)follow_redirects(optional): Follow HTTP redirects (default: true)
Example:
{
"url": "https://api.github.com/user",
"headers": ["Authorization: token YOUR_TOKEN"],
"timeout": 15
}
2. curl_post
Execute HTTP POST requests.
Parameters:
url(required): The URL to requestdata(required): POST data to sendcontent_type(optional): Content-Type header (default: "application/json")headers(optional): Array of additional headerstimeout(optional): Timeout in seconds (default: 10, max: 30)
Example:
{
"url": "https://api.example.com/data",
"data": "{\"key\": \"value\"}",
"content_type": "application/json",
"headers": ["Authorization: Bearer TOKEN"]
}
3. curl_custom
Execute custom curl commands with full control.
Parameters:
args(required): Array of curl arguments (without the 'curl' command)timeout(optional): Timeout in seconds (default: 10, max: 30)
Example:
{
"args": ["-X", "PUT", "-H", "Content-Type: application/json", "-d", "{\"status\": \"updated\"}", "https://api.example.com/resource/123"],
"timeout": 20
}
4. curl_download
Download files and get metadata.
Parameters:
url(required): The URL to download fromoutput_file(optional): Output file pathtimeout(optional): Timeout in seconds (default: 30, max: 30)
Example:
{
"url": "https://example.com/file.pdf",
"output_file": "/tmp/downloaded_file.pdf"
}
Security Features
- URL Validation: Only HTTP and HTTPS URLs allowed
- Argument Filtering: Dangerous curl flags are blocked
- Output Limits: Maximum 1MB output size to prevent memory issues
- Timeouts: All requests have configurable timeouts
- Safe Defaults: Reasonable default values for all parameters
Blocked Operations
For security, the following curl operations are restricted:
- File uploads (
--upload-file,--form) - Config file loading (
--config) - Unrestricted file output (controlled through specific tools)
- Binary data uploads
- Trace file generation
Usage Examples
Basic GET Request
# Through MCP client
{
"tool": "curl_get",
"arguments": {
"url": "https://httpbin.org/get"
}
}
POST with JSON Data
{
"tool": "curl_post",
"arguments": {
"url": "https://httpbin.org/post",
"data": "{\"message\": \"hello world\"}",
"content_type": "application/json"
}
}
Custom Headers
{
"tool": "curl_get",
"arguments": {
"url": "https://api.github.com/user",
"headers": [
"Authorization: token ghp_xxxxxxxxxxxx",
"User-Agent: MyApp/1.0"
]
}
}
Running the Server
# Development mode
npm run dev
# Production mode
npm run build
npm start
Integration with Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"curl": {
"command": "node",
"args": ["/path/to/curl-mcp-server/build/index.js"]
}
}
}
Error Handling
The server provides detailed error messages for:
- Invalid URLs
- Timeout errors
- Curl execution failures
- Output size limits exceeded
- Security violations
Limitations
- Maximum request timeout: 30 seconds
- Maximum output size: 1MB
- Only HTTP/HTTPS protocols supported
- Certain curl flags are blocked for security
Contributing
Feel free to submit issues and enhancement requests. Make sure to test any changes thoroughly, especially security-related modifications.
License
MIT License - see LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.