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

Q: How can I index my Ghost (Publishing & Newsletter Platform API) data with LlamaIndex?

Use the McpToolSpec after initializing the client. It will automatically convert the MCP tools, like contentlistposts, into a format LlamaIndex can use to ingest data directly into a knowledge base.

Turn your Ghost publication into a searchable knowledge base for your LlamaIndex RAG apps. Ground your agent in real data.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Entire Publication

Feed your entire Ghost site into a LlamaIndex vector store. Your agent calls `content_list_posts`, `content_list_pages`, and `content_list_tags` to pull all public content into a structured index. Once it's indexed, you can ask complex questions about your own articles. LlamaIndex finds the relevant text from your Ghost data and uses it to give you a factual answer, not a guess.

Build a Content-Aware LlamaIndex Agent

This is more than just reading data; it's about acting on it. Your RAG app can query the index to find posts on a topic, then use `admin_update_post` to add a 'Related Articles' section to them automatically. Your agent can also use `admin_list_members` and `admin_list_newsletters` to build an index of audience activity. Now you can ask, 'Which members got the last three newsletters?' and get an answer based on real API calls.

Ground Your Agent in Facts, Not Fiction

Stop your agent from making things up. Giving it access to this MCP Server forces it to use tools like `content_get_settings` and `content_list_tiers` to get hard data from your Ghost site. When your agent needs to know your site's title or your membership prices, it doesn't hallucinate. It makes a direct API call, indexes the result, and uses that specific data in its response. It's the only way to trust the output.

Setup guide

Set up Ghost (Publishing & Newsletter Platform API) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Ghost (Publishing & Newsletter Platform API) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Ghost (Publishing & Newsletter Platform API) tools.",
)
response = await agent.run("List recent Ghost (Publishing & Newsletter Platform API) data")

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 LlamaIndex

Use the `McpToolSpec` after initializing the client. It will automatically convert the MCP tools, like `content_list_posts`, into a format LlamaIndex can use to ingest data directly into a knowledge base.

Yes. Once you've equipped your agent with the tools, it can call `admin_create_post` just like any other function. You can build RAG apps that summarize indexed content and then create a new post with the summary.

LlamaIndex is built for RAG—it excels at turning the output of tools like `content_list_posts` into a searchable index. Other frameworks might just execute the call, but LlamaIndex makes the data reusable for future queries.

Yes, the tool supports Ghost's NQL filtering. You can pass a filter string like 'tag:my-tag' to get only the posts you need, which is great for building targeted indexes.

No, your key stays on the Vinkius-managed server. However, be aware that when your LlamaIndex app uses tools like `admin_list_members`, you are choosing to pull that member data and store it in your own vector index. The MCP server itself remains stateless.

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