How do I get a Content API Key for Ghost?

Log in to your Ghost Admin dashboard, navigate to Settings > Integrations, and add a Custom Integration. You will find the Content API Key there.

Can I publish new posts using this integration?

No, this integration uses the Content API which is read-only. It is designed to safely retrieve and query your published content.

What is the Base URL format?

Your Base URL is the root domain where your Ghost site is hosted, for example: 'https://demo.ghost.io'. Do not include '/ghost/api/'.

How do I fetch related tags and authors for a post?

Use the 'include' parameter in the 'get_post_by_slug' tool and pass the string 'tags,authors'.

Ghost MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: Ghost
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Ghost through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Ghost "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Ghost?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Ghost MCP Server

Connect your Ghost publication to any AI agent to automate your content management workflows through the Model Context Protocol (MCP). Ghost is a powerful headless Node.js CMS tailored for modern publishing. This MCP server enables you to retrieve published posts, manage taxonomy tags, and fetch site configurations directly through natural conversation using the Ghost Content API.

Pydantic AI validates every Ghost tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

Key Features

Content Discovery — List all published blog posts and static pages, retrieving detailed HTML content and metadata.
Taxonomy Oversight — Retrieve and list all categorization tags to understand your content architecture.
Author Management — Fetch profile details for active writers and contributors across the publication.
Site Configuration — Access global settings, routing rules, and title schemas programmatically.
Subscription Insights — Retrieve active membership tiers to understand paywall rules and pricing layers.
Real-time Synchronization — Keep your headless CMS content accessible to your AI assistant without leaving your primary workspace.

The Ghost MCP Server exposes 11 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Ghost to Pydantic AI via MCP

Follow these steps to integrate the Ghost MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 11 tools from Ghost with type-safe schemas

Why Use Pydantic AI with the Ghost MCP Server

Pydantic AI provides unique advantages when paired with Ghost through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Ghost integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Ghost connection logic from agent behavior for testable, maintainable code

Ghost + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Ghost MCP Server delivers measurable value.

Type-safe data pipelines: query Ghost with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Ghost tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Ghost and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Ghost responses and write comprehensive agent tests

Ghost MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect Ghost to Pydantic AI via MCP:

get_author_details

Get author profile

get_page_by_slug

Get page details

get_post_by_slug

Get post details

get_site_settings

Get site settings

get_tag_details

Get tag metadata

list_blog_authors

List authors

list_content_tags

List categories/tags

list_published_posts

List published posts

list_static_pages

List static pages

list_subscription_tiers

List subscription tiers

verify_api_connection

Check connection

Example Prompts for Ghost in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Ghost immediately.

"List the 5 most recent published posts."

"Get the content of the post with the slug 'welcome'."

"List all active subscription tiers."

Troubleshooting Ghost MCP Server with Pydantic AI

Common issues when connecting Ghost to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Ghost + Pydantic AI FAQ

Common questions about integrating Ghost MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Ghost MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.