About
The Ghost MCP Server exposes Ghost CMS operations as MCP tools, enabling AI clients like Cursor or Claude Desktop to create tags, upload images, and publish posts directly through a unified protocol.
Capabilities
Ghost MCP Server Overview
Ghost MCP Server is a lightweight, Node‑based implementation of the Model Context Protocol (MCP) that bridges AI assistants such as Claude Desktop or Cursor with a Ghost CMS instance. By exposing Ghost’s administrative endpoints as MCP tools, the server allows AI agents to perform full content‑management workflows—creating tags, uploading images, and publishing posts—directly from within the assistant’s natural‑language interface. This eliminates the need for developers to manually interact with Ghost’s REST API, streamlining content creation and editorial automation.
The server solves a common pain point for developers building AI‑powered publishing pipelines: the lack of a unified, schema‑driven interface to Ghost. Instead of writing bespoke code for each API call, an AI client can query the server’s root endpoint () to discover available resources and tools. Ghost’s data models ( and ) are represented with clear schemas, ensuring type safety and predictable responses. The tools—, , , and —encapsulate the most frequent CMS actions, each with concise input definitions and well‑structured outputs that match the underlying resource types.
Key capabilities include:
- Tag management: Create new tags or retrieve existing ones, automatically handling slug generation and duplication checks.
- Image uploading: Fetch an external image URL and store it in Ghost’s media library, returning the accessible URL and alt text for later use.
- Post creation: Build rich posts with optional scheduling, SEO metadata, and featured images. The tool automatically resolves tag names to IDs, creating missing tags on the fly.
- Schema‑driven interaction: All resources and tool inputs/outputs adhere to MCP’s type system, enabling AI clients to validate requests before execution.
Real‑world use cases span from automated blog posting in response to news feeds, to dynamic content generation for newsletters, and even voice‑controlled editorial workflows where an AI assistant drafts and schedules posts based on conversational prompts. Developers can integrate Ghost MCP Server into their existing CI/CD pipelines, serverless functions, or local development environments with minimal configuration—just the Ghost Admin API URL and key.
What sets this server apart is its comprehensive, opinionated toolset that covers the entire Ghost content lifecycle while remaining fully compliant with MCP. By exposing a consistent, typed interface, it empowers AI assistants to act as first‑class editors, reducing friction for content teams and accelerating the deployment of AI‑driven publishing solutions.
Related Servers
MarkItDown MCP Server
Convert documents to Markdown for LLMs quickly and accurately
Context7 MCP
Real‑time, version‑specific code docs for LLMs
Playwright MCP
Browser automation via structured accessibility trees
BlenderMCP
Claude AI meets Blender for instant 3D creation
Pydantic AI
Build GenAI agents with Pydantic validation and observability
Chrome DevTools MCP
AI-powered Chrome automation and debugging
Weekly Views
Server Health
Information
Explore More Servers
Connpass User MCP Server
Fetch Connpass user and event data via Model Context Protocol
Mobile MCP
Unified mobile automation across iOS, Android, simulators and real devices
Strava MCP Server
Fetch athlete activity data via language models
GitHub MCP Tool
Manage model context directly in GitHub repositories
Symfony MCP Server
Build AI agents directly in your Symfony applications
MCP SSH Server
Secure, background SSH command execution via MCP