Dynamically scan and analyze potentially malicious URLs using the urlDNA.io
The urlDNA MCP Server
enables native tool use for security-focused LLM agents like OpenAI GPT-4.1 and Claude 3 Desktop, providing a direct interface to interact with the urlDNA threat intelligence platform via API.
The urlDNA MCP
server is already hosted and available at:
https://mcp.urldna.io/sse
This server is accessible over Server-Sent Events (SSE) protocol, which supports streaming interactions between LLMs and the backend tools.
You can use it directly with any platform or LLM supporting the mcp
specification (e.g., Claude Desktop, OpenAI GPT-4.1).
The following tools are exposed by the MCP interface:
Tool | Description |
---|---|
new_scan | Submit a new scan for a given URL |
get_scan | Retrieve a scan by ID |
search | Search scans using text, domain, or filters |
fast_check | Lightweight phishing detection via content + redirect analysis |
To integrate the urlDNA MCP server
in Claude Desktop, update your Claude configuration (typically claude.config.json
or equivalent) like so:
{
"mcpServers": {
"urlDNA": {
"command": "python",
"args": [
"<YOUR_PATH>/run.py"
],
"env": {
"authorization": "<urlDNA_API_KEY>"
}
}
}
}
Replace
<YOUR_PATH>
with the actual path torun.py
, and<urlDNA_API_KEY>
with your API key from https://urldna.io.
Once configured, you can prompt Claude with natural language requests like:
"Search in urlDNA for malicious scans with title like paypal"
Claude will automatically call the correct tool and return results from the urlDNA
platform.
from openai import OpenAI
# Initialize OpenAI client (assumes API key is set via env var or config)
client = OpenAI()
response = client.responses.create(
model="gpt-4.1",
input=[
{
"role": "system",
"content": [{"type": "input_text", "text": "You are a cybersecurity analyst using urlDNA."}]
},
{
"role": "user",
"content": [{"type": "input_text", "text": "Search in urlDNA malicious scan with title like paypal"}]
}
],
text={"format": {"type": "text"}},
reasoning={},
tools=[
{
"type": "mcp",
"server_label": "urlDNA",
"server_url": "https://mcp.urldna.io/sse",
"headers": {
"Authorization": "Bearer <URLDNA_API_KEY>"
},
"allowed_tools": ["new_scan", "get_scan", "search", "fast_check"],
"require_approval": "never"
}
],
temperature=0.7,
top_p=1,
max_output_tokens=2048,
store=True
)
print(response.output)
Install dependencies:
pip install -r requirements.txt
For support or API access, visit https://urldna.io or email urldna@urldna.io.
Leverage Notte Web AI agents & cloud browser sessions for scalable browser automation & scraping workflows
Provides web context to LLMs using Cloudflare's Browser Rendering API.
High-quality screenshot capture optimized for Claude Vision API. Automatically tiles full pages into 1072x1072 chunks (1.15 megapixels) with configurable viewports and wait strategies for dynamic content.
Access YouTube video transcripts and translations using the YouTube Translate API.
A browser screenshot tool to capture scrolling screenshots of webpages using Playwright, with support for intelligent section identification and multiple output formats.
A server for browser automation using Google Chrome, based on the MCP framework.
Scrape Weibo user information, feeds, and perform searches.
Playwright MCP server
AI tools for web scraping, crawling, browser control, and web search via the Oxylabs AI Studio API.
Discovers and collects MCP servers from the internet.