Bring Blogging
to Pydantic AI
Learn how to connect Ghost to Pydantic AI and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Ghost MCP Server?
Connect your Ghost publishing account to any AI agent and take full control of your content management and membership workflows through natural conversation.
What you can do
- Content Orchestration — List and manage all blog posts (published, draft, scheduled) and retrieve detailed HTML content and metadata programmatically
- Member Intelligence — Query your subscriber directory and retrieve detailed profiles, including join dates and membership tiers to monitor audience growth
- Site Navigation — List and oversee static site pages (About, Contact) and manage content tags to maintain a perfectly organized site taxonomy
- Publishing Control — Create new posts or drafts and update publishing statuses directly through your agent to streamline your editorial pipeline
- Site Visibility — Retrieve general site settings, newsletter configurations, and active membership offers using natural language commands
How it works
1. Subscribe to this server
2. Retrieve your Admin API Key and Admin Domain from Ghost (Settings > Integrations > Custom Integration)
3. Start managing your digital publication from Claude, Cursor, or any MCP client
No more manual dashboard navigation to check post statuses or member counts. Your AI acts as your dedicated content strategist and site manager.
Who is this for?
- Content Managers — instantly retrieve post details and manage drafts without opening the Ghost admin panel
- Digital Publishers — monitor membership tiers and verify newsletter configurations using natural language
- Marketing Teams — automate site settings querying to orchestrate cross-platform content strategies
Built-in capabilities (10)
Requires a title and supports optional HTML content. The post is created as a "draft" by default but can be set to "published" immediately. Create a new Ghost post or draft
Essential for reviewing the full content of an article. Get details for a specific post
Essential for verifying site identity. Get Ghost site settings and configuration
Includes emails, status, and join dates. List all site members
g., Free, Premium) available on the site. Useful for understanding the subscription structure. List membership tiers and plans
Newsletters are used to send content updates to members. List all configured newsletters
List active membership offers
g., About, Contact) defined on the Ghost site. Pages are similar to posts but used for non-blog content. List all static site pages
Includes basic metadata and post IDs for detailed retrieval. List all Ghost blog posts
Useful for organizing and filtering posts. List all content tags
Why Pydantic AI?
Pydantic AI validates every Ghost tool response against typed schemas, catching data inconsistencies at build time. Connect 10 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.
- —
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 in Pydantic AI
Ghost and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Ghost to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Ghost in Pydantic AI
The Ghost 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. All 10 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
Ghost for Pydantic AI
Every tool call from Pydantic AI to the Ghost MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I find my Ghost Admin API Key?
Log in to your Ghost admin panel, navigate to Settings > Integrations, click Add custom integration, and copy the Admin API Key and API URL.
What is the Admin Domain?
It is the API URL provided in your custom integration settings (e.g., https://your-site.ghost.io). Do not include the /ghost/api/admin/ part.
Can I publish a post immediately via AI?
Yes! When using the create_post tool, set the status parameter to 'published' to make your content live instantly.
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.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai