How to Use the Censys MCP in OpenAI Agents SDK

Q: How do I configure the Censys MCP Server with the OpenAI Agents SDK?

Install openai-agents via pip and initialize the Censys MCP Server using MCPServerStreamableHttp. Pass this instance directly into the mcpservers list of your OpenAI Agents SDK constructor to enable automatic tool discovery.

Q: How does the OpenAI Agents SDK handle Censys API rate limits?

Your OpenAI Agents SDK agent can call getaccountinfo to check your remaining Censys query quota before running large infrastructure scans. This lets you write logic that pauses agent execution or alerts you when limits are near.

Q: Can the OpenAI Agents SDK agent compare different servers to find configuration drift in Censys?

Yes, the agent runs viewhostdiff to compare two IP addresses and identify differences in open ports or banners. This reveals exactly which servers deviate from your baseline security configuration.

Securely expose internet-wide attack surface data to your OpenAI Agents SDK with strict guardrails and complete execution tracing.

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 OpenAI Agents SDK

Create your Vinkius account to connect Censys to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track host history safely with OpenAI Agents SDK

The `get_host_history` tool pulls chronological scan records for any IP address, allowing your OpenAI Agents SDK system to analyze how a target's open ports shifted over time. Your agent uses this historical Censys timeline to map out infrastructure alterations without needing manual scripts. Because you deploy this on the OpenAI Agents SDK, you can set up guardrails that intercept raw Censys history before your agent processes it. This safety layer ensures your agent doesn't act on outdated threat intelligence or trigger false alerts during automated incident response.

Map certificate networks via MCP Server tools

The `get_certificate_hosts` tool resolves every domain and IP address sharing a specific SSL/TLS certificate fingerprint, feeding this data directly to your OpenAI Agents SDK agent. Your agent calls this Censys endpoint to find hidden staging environments or sister sites sharing the same cryptographic identity. You can pass this Censys MCP Server to your OpenAI Agents SDK constructor as a streamable HTTP resource. The agent auto-discovers these certificate tools, allowing it to pivot from a single suspicious domain to a complete list of linked internet hosts.

Group exposed services by geographic location

The `aggregate_hosts` tool groups Censys search results by fields like autonomous system name or country, sending structured bucket counts directly to your OpenAI Agents SDK workflow. Your agent uses this geographic aggregation to pinpoint which regional subnets host the highest number of open database ports. This tool feeds structured Censys bucket counts directly into your OpenAI Agents SDK reasoning loop. By combining this with the SDK's multi-agent handoffs, a specialized analysis agent can pass these geographic clusters to a remediation agent for targeted patching.

Setup guide

Set up Censys MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Censys tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Censys tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Censys tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Censys Agent",
            instructions="You have access to Censys tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip and initialize the Censys MCP Server using `MCPServerStreamableHttp`. Pass this instance directly into the `mcp_servers` list of your OpenAI Agents SDK constructor to enable automatic tool discovery.

Yes, you control this through the OpenAI Agents SDK's built-in guardrails and Censys tool filtering. You can intercept Censys tool calls before execution to block heavy queries or restrict access to specific host search functions.

Your OpenAI Agents SDK agent can call `get_account_info` to check your remaining Censys query quota before running large infrastructure scans. This lets you write logic that pauses agent execution or alerts you when limits are near.

Yes, the agent runs `view_host_diff` to compare two IP addresses and identify differences in open ports or banners. This reveals exactly which servers deviate from your baseline security configuration.

The Censys MCP Server runs in a secure, zero-trust sandbox that does not store your queried IP addresses or certificates. Your target queries go directly to the Censys API endpoint over encrypted HTTP, ensuring your internal infrastructure lists never leak to external training sets.

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