How to Use the Ghost MCP in Pydantic AI

Q: How do I initialize the Ghost MCP Server in Pydantic AI?

Use the MCPToolset class pointing to your Vinkius Ghost MCP HTTP endpoint. Pass this toolset directly into the Pydantic AI Agent constructor using the toolsets parameter.

Audit Ghost publications with strict, type-safe runtime validation using Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Ghost to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Ghost API responses with Pydantic AI

Stop worrying about silent Ghost API failures or unexpected null fields in your blog data by using Pydantic AI. When your Pydantic AI agent calls `get_post_by_slug` or `list_published_posts`, this framework validates the incoming Ghost JSON against strict Python types at runtime. If Ghost modifies its payload schema, your Pydantic AI agent catches the mismatch instantly. You get clear, actionable Pydantic AI traceback errors instead of corrupt Ghost data passing silently into your production database.

Ensure type-safe taxonomy and author mapping

Pulling structured Ghost data requires rock-solid schemas, which is why Pydantic AI is perfect for nested tags. Your Pydantic AI agent uses `list_content_tags` and `get_tag_details` to extract your Ghost publication categories safely. The Pydantic AI framework parses these Ghost responses alongside `list_blog_authors` to guarantee every author profile fits your exact model definitions. This Ghost MCP Server integration ensures your Pydantic AI taxonomy mapping scripts never break due to unexpected string formats.

Safe configuration audits of static pages

Monitor your Ghost site's structural health by querying `list_static_pages` and `get_page_by_slug` using Pydantic AI. The Pydantic AI agent verifies settings using `get_site_settings` to confirm your Ghost site setup matches your local deployment expectations. Using this Ghost MCP setup with Pydantic AI means your validation models run before your agent can act on the data. You can safely check your Ghost site configuration without worrying about malformed inputs crashing your Pydantic AI background workers.

Setup guide

Set up Ghost MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "ghost-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Ghost tools.",
)

result = await agent.run("List recent Ghost transactions")
print(result.output)

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 CMS. 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 Pydantic AI

Use the `MCPToolset` class pointing to your Vinkius Ghost MCP HTTP endpoint. Pass this toolset directly into the Pydantic AI `Agent` constructor using the `toolsets` parameter.

Yes, the Pydantic AI framework supports both Streamable HTTP and SSE transports for Ghost. This allows your Pydantic AI agent to fetch large Ghost datasets like `list_published_posts` efficiently.

It validates every Ghost response against your strict Pydantic AI schemas. If a Ghost tool like `get_author_details` returns unexpected fields, the Pydantic AI framework raises a validation error immediately.

Yes, this Pydantic AI framework is model-agnostic. You can run local models or commercial APIs to process your Ghost `list_subscription_tiers` data without changing your Pydantic AI tool configuration.

Your Ghost API credentials and reader billing tiers are processed strictly in-memory by Pydantic AI. Vinkius handles the Ghost connection using zero-trust isolates, ensuring your live Ghost CMS data remains completely private.

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