How to Use the Ghost (Publishing & Newsletter Platform API) MCP in LangChain

Q: Can my LangChain agent create new members in Ghost?

Yes. The admincreatemember tool lets your agent add a new member, including their email and name. You can chain this with other tools to, for example, add a member and then assign them to a specific post.

Q: What's the best way to manage post drafts using the Ghost (Publishing & Newsletter Platform API) and LangChain?

Use the admincreatepost tool with the status parameter set to 'draft'. Your agent can create the draft, then you can have a separate chain that uses adminupdatepost to publish it after a human review step.

Q: Can my agent check for existing posts before creating a new one?

Absolutely. Your chain should first call adminlistposts with a filter for the title. If the result is empty, then proceed with the admincreatepost call.

Build content pipelines for your Ghost publication with LangChain agents. Chain tools, trace calls, and automate your workflow.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ghost (Publishing & Newsletter Platform API) MCP to LangChain

Create your Vinkius account to connect Ghost (Publishing & Newsletter Platform API) 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 Ghost (Publishing & Newsletter Platform API) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Post and Member Management

Connect `admin_create_post` and `admin_update_post` to let your agent draft and refine content in a single run. Your agent can list members with `admin_list_members`, check their status, and then create a members-only post just for them. Because LangChain builds multi-step chains, your agent can do real work. It can fetch all public posts with `content_list_posts`, find one that's outdated, use `admin_update_post` to fix it, and then draft a follow-up with `admin_create_post`. Each step's output feeds the next.

Automate Newsletters with a LangChain Agent

Build an agent that writes your next newsletter. It starts by pulling your site's branding with `content_get_settings` and then scans recent articles using `content_list_posts` to find topics. The agent uses that data to draft a new summary post with `admin_create_post`. You can see the whole thing happen in LangSmith, watching the agent reason about which articles to include before it builds the final payload for Ghost.

Connect Ghost to Your Other Systems

Use this MCP Server to make Ghost a predictable step in a bigger process. Your agent can read public data from your site using tools like `content_list_authors` or `content_list_tags`. Then, it passes that information to another tool in your chain. Maybe you want to sync author bios to a CRM or archive post tags in a database. Ghost just becomes another API your agent knows how to use.

Setup guide

Set up Ghost (Publishing & Newsletter Platform API) 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 Ghost (Publishing & Newsletter Platform API) 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({
    "ghost-publishing-newsletter-platform-api-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 Ghost (Publishing & Newsletter Platform API) 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 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 (Publishing & Newsletter Platform API) 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 (Publishing & Newsletter Platform API) MCP in LangChain

Install the Vinkius adapter, point it to your server endpoint, and call `client.get_tools()`. This returns a list of tools you can pass directly to your LangChain agent constructor.

Yes. The `admin_create_member` tool lets your agent add a new member, including their email and name. You can chain this with other tools to, for example, add a member and then assign them to a specific post.

Use the `admin_create_post` tool with the `status` parameter set to 'draft'. Your agent can create the draft, then you can have a separate chain that uses `admin_update_post` to publish it after a human review step.

Absolutely. Your chain should first call `admin_list_posts` with a filter for the title. If the result is empty, then proceed with the `admin_create_post` call.

Your key is stored by Vinkius, not your agent's code. This MCP server runs in a secure sandbox, and your LangChain agent only uses an ephemeral Vinkius token to make calls. The server proxies the request, injecting the Ghost key on the backend so it's never exposed.

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