How to Use the Ghost MCP in OpenAI Agents SDK

Q: How do I connect the Ghost MCP Server to the OpenAI Agents SDK?

Install the package using pip install openai-agents. Initialize the connection with MCPServerStreamableHttp(params=MCPServerStreamableHttpParams(url="...")). Pass that into your agent constructor under mcpservers=server and set cacheToolsList=True to speed up tool discovery.

Q: Can the Ghost MCP Server publish articles immediately?

Yes. The createpost tool defaults to creating a draft. You can override this behavior to publish the post immediately if your workflow requires it.

Q: Does Ghost and the OpenAI Agents SDK support newsletter management?

Your agent calls listnewsletters to view all configured email updates. It cannot send the emails directly through this specific endpoint. The tool only reads the existing newsletter configuration.

Q: How do I verify my site settings using this integration?

The getsitesettings tool returns your core configuration data. Your agent uses this to confirm it is talking to the correct instance before modifying any content. This prevents accidental writes to a staging environment.

Connect your Ghost CMS directly to the OpenAI Agents SDK for automated publishing and membership management.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ghost MCP to OpenAI Agents SDK

Create your Vinkius account to connect Ghost 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 Ghost with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Content Publishing

Your agent uses `create_post` to draft or publish new articles directly to Ghost. You pass a title and optional HTML content, and the system handles the rest. Setting it to draft by default gives your human editors time to review before anything goes live. The OpenAI Agents SDK guardrails ensure your agent doesn't accidentally push an unfinished draft to your live site. You can build a specialized writing agent that hands off the final review to a publishing agent. That second agent then uses `get_post_details` to verify the formatting before flipping the status to published.

Manage Ghost Members with the MCP Server

The `list_members` tool pulls down your entire subscriber base, including their emails, join dates, and current status. This gives your agent immediate context on who is reading your content. You get raw data instead of guessing about audience growth. Combine this with `list_membership_tiers` to see exactly which plans those users belong to. If an agent notices a drop in premium conversions, it can check `list_offers` to see what promotions are currently active. You track all of this reasoning through the OpenAI dashboard tracing features.

Audit Site Structure and Tags

Calling `list_tags` retrieves every content tag you use to organize your blog. Your agent maps out your site hierarchy before writing a single word. It knows exactly where a new post fits into your existing categories. When auditing older content, the agent runs `list_posts` to grab basic metadata and IDs. It then iterates through specific articles using `get_post_details`. If your site layout needs a check, `list_pages` pulls the static routing for your About or Contact sections.

Setup guide

Set up Ghost 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 Ghost tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using `pip install openai-agents`. Initialize the connection with `MCPServerStreamableHttp(params=MCPServerStreamableHttpParams(url="..."))`. Pass that into your agent constructor under `mcp_servers=[server]` and set `cacheToolsList=True` to speed up tool discovery.

Yes. The `create_post` tool defaults to creating a draft. You can override this behavior to publish the post immediately if your workflow requires it.

Your agent calls `list_newsletters` to view all configured email updates. It cannot send the emails directly through this specific endpoint. The tool only reads the existing newsletter configuration.

The `get_site_settings` tool returns your core configuration data. Your agent uses this to confirm it is talking to the correct instance before modifying any content. This prevents accidental writes to a staging environment.

This server accesses raw subscriber emails and join dates via `list_members`. The connection runs through a V8 Isolate Sandbox that destroys itself after the session ends. Your user data never persists in the middle layer.

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