How to Use the Caddy Server MCP in OpenAI Agents SDK

Q: How do I register the Caddy Server MCP toolset with the OpenAI Agents SDK?

Instantiate MCPServerStreamableHttp with your Vinkius endpoint URL. Pass that server instance in the mcpservers list when initializing your Agent object. Set cacheToolsList=True to keep tool discovery fast.

Q: Can the OpenAI Agents SDK safely run adaptconfig without applying changes?

Yes, your agent can run adaptconfig to validate Caddyfile syntax. The tool converts the raw configuration to JSON without modifying the active state of your running Caddy Server.

Q: How does OpenAI Agents SDK handle upstream failures detected by getupstreams?

The agent calls getupstreams to check backend health. If it finds a bad node, it can use replaceconfig to update the upstream list and route traffic away from the failing backend.

Q: What is the fastest way to shut down Caddy Server using this integration?

The agent can call stopserver to gracefully shut down the process. Make sure your SDK agent has explicit permission to run this action, as it stops all routing immediately.

Control your Caddy Server configurations and certs directly inside safe, production-grade OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Caddy Server MCP to OpenAI Agents SDK

Create your Vinkius account to connect Caddy Server 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 Caddy Server with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe Caddy Server Config Changes with OpenAI Agents SDK

Using `get_config`, your OpenAI Agents SDK can instantly inspect your Caddy Server routing table and safely push updates with `replace_config` or `append_config`. Because you are running OpenAI Agents SDK, this MCP Server lets you set strict validation guardrails that inspect these JSON payloads before they hit your live proxy. If a generated Caddyfile has a syntax error, the agent catches it early. It can run `adapt_config` to test the JSON schema translation without breaking the active server. This prevents bad routes from taking down your production web traffic.

Automated PKI Management via MCP Server

By running `get_pki_ca_certs`, this MCP Server lets your OpenAI Agents SDK pull down active Caddy Server certificate chains and inspect local authority details with `get_pki_ca`. The agent handles the tedious work of checking expiration dates and testing trust chains. When it detects an issue, it triggers alerts or runs automated renewals directly inside your OpenAI Agents SDK runtime.

Dynamic Upstream Control

Querying `get_upstreams` allows your OpenAI Agents SDK to verify which backend targets are healthy and which ones are dropping requests. If a backend node starts acting up, the agent can run `delete_config` to pull the failing node out of the load balancer pool. It keeps your site online without waiting for a human operator to wake up.

Setup guide

Set up Caddy Server 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 Caddy Server tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Caddy Server 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="Caddy Server Agent",
            instructions="You have access to Caddy Server 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 Caddy Server. 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 Caddy Server 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 Caddy Server MCP in OpenAI Agents SDK

Instantiate `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass that server instance in the `mcp_servers` list when initializing your `Agent` object. Set `cacheToolsList=True` to keep tool discovery fast.

Yes, your agent can run `adapt_config` to validate Caddyfile syntax. The tool converts the raw configuration to JSON without modifying the active state of your running Caddy Server.

The agent calls `get_upstreams` to check backend health. If it finds a bad node, it can use `replace_config` to update the upstream list and route traffic away from the failing backend.

The agent can call `stop_server` to gracefully shut down the process. Make sure your SDK agent has explicit permission to run this action, as it stops all routing immediately.

Your Caddy Server JSON configurations and PKI certificates never leave your secure Vinkius sandbox. This integration uses token-based headers to authenticate requests, ensuring your private TLS keys and routing rules remain completely isolated from unauthorized external access.

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