Ghost MCP
An MCP server for the Ghost blogging platform with Server-Sent Events (SSE) transport support.
Ghost MCP Server with SSE Transport
This repository contains a Model Context Protocol (MCP) server implementation for the Ghost blogging platform with Server-Sent Events (SSE) transport support.
Features
- Supports both SSE and stdio transports
- Provides access to Ghost Admin API functionality through MCP tools
- Manage Ghost blog posts, pages, and tags
- Secure by default with non-root user in Docker
- Environment variable configuration
- Health check endpoint
Quick Start
Environment Setup
-
Copy the example environment file:
cp .env.example .env -
Edit the
.envfile with your Ghost API credentials:GHOST_URL=https://your-ghost-blog.com GHOST_KEY_ID=your_ghost_key_id_here GHOST_KEY_SECRET=your_ghost_key_secret_here PORT=3064 NODE_ENV=production
Using Docker Compose
The easiest way to run the server is with Docker Compose:
docker-compose up -d
This will build the image if needed and start the server in detached mode.
Using Docker Directly
You can also build and run the Docker image directly:
# Build the image
docker build -t oculair/ghost-mcp:1.0.0 .
# Run the container
docker run -p 3064:3064 --env-file .env --rm -it oculair/ghost-mcp:1.0.0
Multi-Architecture Build
To build for multiple architectures (amd64 and arm64):
-
Enable Docker Buildx:
docker buildx create --use --name multiarch-builder docker buildx inspect --bootstrap -
Build and push:
docker buildx build --platform linux/amd64,linux/arm64 \ -t oculair/ghost-mcp:1.0.0 \ --push . -
Verify the multi-architecture image:
docker manifest inspect oculair/ghost-mcp:1.0.0
Development
Project Structure
.
├── everything/
│ ├── src/
│ │ ├── core/ # Core server implementation
│ │ ├── tools/ # MCP tool implementations
│ │ ├── transports/ # Transport implementations (SSE, stdio)
│ │ └── index.js # Main entry point
│ └── package.json # Node.js dependencies
├── .env.example # Example environment variables
├── .gitignore # Git ignore file
├── compose.yaml # Docker Compose configuration
├── Dockerfile # Docker build configuration
└── README.md # This file
Available Tools
The server provides the following MCP tools:
- Posts:
create_ghost_post,list_ghost_posts,update_ghost_post,delete_ghost_post - Pages:
create_ghost_page,list_ghost_pages,update_ghost_page,delete_ghost_page - Tags:
create_ghost_tag,update_ghost_tag
For detailed information about each tool and its parameters, see the everything/README.md file.
Debugging
To debug the container, you can run it with an interactive shell:
docker run -p 3064:3064 --env-file .env --rm -it --entrypoint bash oculair/ghost-mcp:1.0.0
Usage with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ghost": {
"url": "http://localhost:3064/sse",
"disabled": false,
"alwaysAllow": []
}
}
}
相關伺服器
Scout Monitoring MCP
贊助Put performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
贊助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
MCP LaTeX Server
Create, edit, and manage LaTeX files. Requires an external LaTeX distribution like MiKTeX, TeX Live, or MacTeX.
ArchiveNet
A context insertion and search server for Claude Desktop and Cursor IDE, using configurable API endpoints.
Elementor WordPress MCP Server
An MCP server for WordPress and Elementor, enabling AI assistants to manage content and build pages.
WRG MCP Server
A server providing tools for weapon recoil generation and visualization via HTTP endpoints.
Ollama MCP Server
Integrate local Ollama LLM instances with MCP-compatible applications.
MCP-Portainer Bridge
Manage Docker containers through the Portainer API.
MCPOmni Connect
A universal command-line interface (CLI) gateway to the MCP ecosystem, integrating multiple MCP servers, AI models, and transport protocols.
agent-friend
Universal tool adapter — @tool decorator exports Python functions to OpenAI, Claude, Gemini, MCP, JSON Schema. Audit token costs.
Tiktoken MCP
Count tokens using OpenAI's tiktoken library.
YepCode
Execute any LLM-generated code in the YepCode secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages