How to Use the Censys MCP in LangChain

Q: How do I run a basic host search with Censys and LangChain?

You pass the searchhosts tool to your LangChain agent with a query like 'services.port: 80 and location.countrycode: US'. The agent will execute the search against the Censys MCP Server and return the list of matching IPs.

Q: Can a LangChain agent check my Censys API quota?

Yes. Just include the getaccountinfo tool in the list you provide to your agent. Then you can ask it 'What's my remaining Censys quota?' and it will call the tool to get the answer.

Q: What's the best way to find all hosts sharing a certificate using Censys and LangChain?

Start by having your agent find a certificate with searchcertificates. Then, in the next step of the chain, have it pass the certificate's fingerprint to the getcertificatehosts tool. This will return all hosts associated with that certificate.

Q: How should my agent handle paginated search results from Censys?

The searchhosts and searchcertificates tools return a cursor for pagination. You need to design your agent's logic to check for this cursor and re-call the tool with the cursor parameter until no more results are returned.

Build security agents in LangChain that chain Censys lookups to map your entire attack surface.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Censys MCP to LangChain

Create your Vinkius account to connect Censys to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Censys with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Attack Surface Discovery

Give your LangChain agent a simple goal: find all web servers in a specific region. The agent can use `search_hosts` to pull a list of IPs, then chain that output directly into `get_host` for each one. Now you have a detailed inventory of every open port and service banner. This isn't just a one-off script. You're building a reusable chain that can run on a schedule. Your agent makes the decisions, calling the right Censys tool for the job. It can even use `get_account_info` to check its own quota before starting a large scan. That's a smarter, more autonomous way to handle discovery.

Chain Certificate Lookups

Track down every host using a specific SSL certificate. Start with a `search_certificates` query to find a cert by its fingerprint or subject name. Your LangChain agent takes that fingerprint and passes it to `get_certificate_hosts` to get a list of every IP address where it's been seen. This is how you find shared infrastructure or track the rollout of a new certificate. The agent connects the dots for you, turning a single piece of information into a complete map of related assets. It's a simple, powerful chain of MCP tool calls.

Find What Changed with Your LangChain Agent

Your agent can spot changes on a host that you'd miss. It starts by calling `get_host_history` to pull a timeline of scans for a specific IP. When it finds two different snapshots, it feeds them into `view_host_diff`. The output shows exactly what's different—a new port opened, a service banner changed, a certificate swapped out. You can build agents that monitor critical assets and alert you only when a meaningful change happens. No more manually comparing JSON files.

Setup guide

Set up Censys MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Censys tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "censys-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Censys transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Censys. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Censys now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Censys MCP in LangChain

You pass the `search_hosts` tool to your LangChain agent with a query like 'services.port: 80 and location.country_code: US'. The agent will execute the search against the Censys MCP Server and return the list of matching IPs.

Yes. Just include the `get_account_info` tool in the list you provide to your agent. Then you can ask it 'What's my remaining Censys quota?' and it will call the tool to get the answer.

Start by having your agent find a certificate with `search_certificates`. Then, in the next step of the chain, have it pass the certificate's fingerprint to the `get_certificate_hosts` tool. This will return all hosts associated with that certificate.

The `search_hosts` and `search_certificates` tools return a cursor for pagination. You need to design your agent's logic to check for this cursor and re-call the tool with the cursor parameter until no more results are returned.

This server processes public internet scan data, including IP addresses, port information, service banners, and SSL/TLS certificate details. Your Vinkius endpoint token is the only credential needed; all data in transit is encrypted and processed in an ephemeral sandbox.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript