How to Use the Censys MCP in Pydantic AI

Q: How do I initialize the Censys MCP Server using Pydantic AI?

Install pydantic-ai-slimmcp and use the MCPToolset class to connect to your streamable Censys HTTP endpoint. Pass this toolset into the toolsets argument of your Pydantic AI Agent to expose the search tools.

Q: Can I run Censys host searches using structured query syntax in Pydantic AI?

Yes, searchhosts lets you query the internet using service names, ports, and protocols. The Censys search results are returned as structured data that your Pydantic AI agent can easily iterate through and validate.

Run type-safe Censys searches with Pydantic AI to guarantee runtime validation of all host and certificate data.

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 Pydantic AI

Create your Vinkius account to connect Censys to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate certificate metadata with Pydantic AI

The `get_certificate` tool retrieves the complete parsed certificate from Censys, forcing Pydantic AI to validate the nested validity dates and public key info against strict Python models. Your agent uses this verified Censys data to guarantee that no unvalidated cryptographic payloads enter your security pipeline. If a Censys certificate contains non-standard extensions or unexpected null values, the Pydantic AI framework raises a validation error immediately. This strict validation prevents silent failures down the line, ensuring your security pipeline only processes well-formed cryptographic data.

Compare network hosts using structured MCP Server tools

The `view_host_diff` tool compares two IP addresses to highlight differences in open ports, service banners, and TLS configurations, passing a structured delta to your Pydantic AI agent. Your agent uses this Censys comparison to verify that staging servers match your production baseline down to the byte. Because this runs through a Censys MCP Server, the diff payload is typed and structured. Pydantic AI checks the differences against your schema, ensuring your agent receives clear, predictable Censys data structures to evaluate.

Monitor remaining API quota programmatically

The `get_account_info` tool queries your current Censys API usage, remaining query limits, and account tier directly within your Pydantic AI runtime. Your agent runs this check before starting large-scale infrastructure scans to ensure you have enough quota. The returned Censys quota numbers are validated as strict integers by Pydantic AI at runtime. This guarantees your agent doesn't crash on type mismatches when deciding whether to proceed with a scan or pause execution.

Setup guide

Set up Censys MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "censys-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Censys tools.",
)

result = await agent.run("List recent Censys transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]` and use the `MCPToolset` class to connect to your streamable Censys HTTP endpoint. Pass this toolset into the `toolsets` argument of your Pydantic AI Agent to expose the search tools.

Pydantic AI validates the response against strict Censys schemas at runtime. If the API returns unexpected fields, the Pydantic AI agent raises a validation error, preventing your agent from hallucinating or processing corrupt data.

Yes, Pydantic AI is model-agnostic, allowing you to connect your Censys toolset to local models running via Ollama. This setup maintains strict type safety for all returned host and certificate fields.

Yes, `search_hosts` lets you query the internet using service names, ports, and protocols. The Censys search results are returned as structured data that your Pydantic AI agent can easily iterate through and validate.

All transactions run through an isolated, zero-trust V8 sandbox that handles authentication. The Censys MCP Server processes your query parameters in memory and never writes them to disk, keeping your account limits and API usage confidential.

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