
MCP-Censys
A Model Context Protocol server that enables natural language querying of the Censys Search API for domain, IP, and FQDN reconnaissance, providing information about hosts, DNS, certificates, and services in real-time.
README
mcp-censys
mcp-censys is a MCP server that taps into the Censys Search API for real-time domain, IP, and FQDN reconnaissance.
[!CAUTION] This is intended solely as a demonstration and is not production-ready. It is not an officially supported product.
Overview
mcp-censys turns natural language prompts into targeted Censys queries — surfacing host, DNS, cert, and service information in real-time. It's designed to work with Claude Desktop or any other Model Context Protocol (MCP) client.
Built on the official Censys Python SDK, this lightweight container exposes precise reconnaissance tools through Claude-friendly functions.
Features
- Conversational Queries: Natural language access to Censys intel
- Domain and IP Lookup: Get DNS names, ASN, services, and TLS context
- New FQDN Discovery: Find recently seen subdomains from DNS and cert data
- MCP-Compatible Tools: Use directly from Claude Desktop
- Dockerized with .env support: Secure, repeatable usage
- Lightweight API Client: Based on Censys Python SDK
Tools
- lookup_domain - Get comprehensive IPs, DNS names, services, and ASN info for a domain (aggregates data across all results)
- lookup_domain_detailed - Return a sample of 3 individual host records with services, ASN, geo, and TLS data, along with information about total available records
- lookup_ip - Enrich an IP with DNS, ASN, service info, and TLS metadata
- new_fqdns - Find recently observed FQDNs for a domain (via DNS and certs)
- host_services - List open ports and service banners for a given domain or IP
Quick Start Guide
1. Domain Lookup (lookup_domain
)
Returns complete information by aggregating all IPs, DNS names, service banners, and ASN info tied to a specific domain. Useful for understanding what infrastructure a domain resolves to.
Example:
User: What's behind mailchimp.com?
AI: mailchimp.com resolves to multiple IPs operated by The Rocket Science Group (AS2635). The domain exposes ports 80 and 443 with HTTP services, and reverse DNS shows aliases like smtp.mailchimp.com and us1.admin.mailchimp.com. Several servers respond with the banner 'mailchimp-nginx'.
2. Detailed Domain Lookup (lookup_domain_detailed
)
Provides a sample of actual host records (limited to 3) matching a domain query, plus information about how many total records exist.
Example:
User: Show me detailed records for mailchimp.com
AI: I found 42 host records for mailchimp.com. Here's a sample of 3:
IP: 205.201.131.98 - Located in Atlanta, GA (The Rocket Science Group)
Services: HTTP/80, HTTPS/443, SMTP/25
OS: Ubuntu 18.04
IP: 205.201.132.24 - Located in Atlanta, GA (The Rocket Science Group)
Services: HTTP/80, HTTPS/443
TLS: TLSv1.2, RSA 2048-bit
IP: 198.2.131.20 - Located in Atlanta, GA (The Rocket Science Group)
Services: SMTP/25, SMTP/587
TLS: TLSv1.2, DH 2048-bit
There are 39 additional records not displayed.
3. IP Lookup (lookup_ip
)
Provides full context for an IP including DNS names, ASN, TLS certs, services, and location data.
Example:
User: Tell me about 184.29.22.16
AI: 184.29.22.16 is associated with Akamai (AS20940). It has two services exposed: HTTP on port 80 and HTTPS on 443. It's hosted in the United States and uses a TLS certificate issued by Let's Encrypt.
4. New FQDN Discovery (new_fqdns
)
Find recently observed FQDNs for a domain from both DNS records and certificate transparency logs.
Example:
User: What new fqdns has microsoft.com had in the last 3 days?
AI: In the last 3 days, 17 FQDNs were observed for microsoft.com, including:
login.microsoft.com (seen in DNS and certs)
api.microsoft.com (seen in certs only)
graph.microsoft.com (seen in DNS only)
teams.microsoft.com (seen in DNS and certs)
5. Host Services (host_services
)
Quickly identifies what ports are open on a given IP and what services are running.
Examples:
User: What ports are open on example.com?
AI: example.com (93.184.216.34) has the following services:
HTTP on port 80 (last seen 2 hours ago)
HTTPS on port 443 (last seen 2 hours ago)
Installation
# Clone the repository
git clone https://github.com/yourusername/mcp-censys.git
cd mcp-censys
# Build the Docker image
docker build -t mcp/censys .
# .env should contain:
CENSYS_API_ID=your_censys_api_id
CENSYS_API_SECRET=your_censys_api_secret
MCP Configuration
Add this to your Claude Desktop config:
"censys": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--env-file", "/Users/yourname/.env.censys",
"mcp/censys"
]
}
Screenshot
mcp-censys in action via Claude Desktop, using the lookup_domain
, lookup_domain_detailed
and lookup_ip
tools:
This example shows a domain lookup request on
mailchimp.com
, returning IPs, ASN, subdomains, services and infrastructure — all from a natural language query.
This example shows a detailed domain lookup request on
mailchimp.com
, returning IPs, ASN, subdomains, BGP, TLS, information, services and infrastructure.
This example demonstrates an IP lookup on
23.204.1.14
, returning coordinates, forward and reverse DNS and services.
Troubleshooting
No Results Returned:
- Make sure the target is publicly visible
- Check your API key and rate limits
- DNS-based results rely on recent Censys observations
Performance Tips:
- Scan a single domain or IP at a time for faster results
- Use lookup_domain or lookup_ip for focused data
API Response Issues:
- If you experience errors with result formatting, ensure you're using the latest version
- The tools handle pagination automatically - lookup_domain collects all available results, while lookup_domain_detailed shows a limited sample
- For domains with many results, queries may take longer to complete due to multiple API requests
Limitations
- new_fqdns does not represent true "first seen" FQDNs; it filters by last observed timestamps
- This tool is intended for conversational, single-target analysis (not batch scans)
- lookup_domain_detailed only shows 3 records to keep responses manageable, even when more are available
License
MIT License
Acknowledgments
- Censys Python SDK (https://github.com/censys/censys-python)
- Model Context Protocol (https://modelcontextprotocol.io/)
- Claude Desktop (https://www.anthropic.com)
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.