Secure Fetch
Secure fetch to prevent access to local resources
Secure Fetch
This project implements a secure URL fetching tool using FastMCP.
Prerequisites
- Python 3.7+
- uv (Python package installer and environment manager)
Installation
- Install uv if you haven't already:
pip install uv
- Create a new virtual environment and install dependencies:
uv venv source .venv/bin/activate uv pip install fastmcp requests
Usage
- Set the allowlist environment variable (optional):
export SECURE_FETCH_ALLOWLIST="example.com,trusted-domain.org"
- Run the script:
uv run main.py
Features
- Fetches URLs securely
- Resolves domains to IPs
- Checks for private/internal IPs
- Handles redirects (up to 3)
- Supports custom HTTP methods and headers
- Uses an allowlist for trusted domains/IPs
Security Considerations
- The tool prevents access to private/internal IPs unless explicitly allowed
- Only HTTP and HTTPS schemes are permitted
- SNI is set to match the hostname for HTTPS connections
Example Usage
Once the script is running, you can use the fetch_url function to securely fetch URLs. The function will return a dictionary containing the status code, response body, and content length.
Note
This tool is designed for secure URL fetching. Always review and understand the code before using it in your environment.
相关服务器
Bright Data
赞助Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Buienradar
Fetches precipitation data for a given latitude and longitude using Buienradar.
HTML to Markdown MCP
Fetch web pages and convert HTML to clean, formatted Markdown. Handles large pages with automatic file saving to bypass token limits.
powhttp-mcp
MCP server enabling agents to debug HTTP requests better
Rapidproxy
Over 70M+ premium IPs via Rapidproxy - Enjoy easy data extraction, avoiding CAPTCHAs, IP blocks with 220+ locations targeting, non-expiring traffic.
Decodo
Easy web data access. Simplified retrieval of information from websites and online sources.
HTTP Requests
An MCP server for making HTTP requests, enabling LLMs to fetch and process web content.
freesound-mcp
A Model Context Protocol (MCP) server that enables AI applications to search and download audio resources from the Freesound platform via natural language commands.
Oxylabs
Scrape websites with Oxylabs Web API, supporting dynamic rendering and parsing for structured data extraction.
Agentic Deep Researcher
A deep research agent powered by Crew AI and the LinkUp API.
Firecrawl MCP
Adds powerful web scraping and search capabilities to LLM clients like Cursor and Claude.