Ghost MCP Server
A server that integrates Ghost CMS with Claude AI through the FastMCP framework.
Requirements
- Python 3.11+
- uv - Required to run this server
Setup
- Clone the repository
- Create a virtual environment (optional but recommended):
uv venv source .venv/bin/activate # On Windows: .venv\\Scripts\\activate - Install dependencies using uv (dependencies are defined in pyproject.toml):
uv pip install . - Set up environment variables by copying
.env.exampleto.env:cp .env.example .env - Configure your
.envfile with your Ghost API credentials:GHOST_API_KEY=your_ghost_api_key_here GHOST_API_URL=https://your-ghost-blog.com/ghost/api/admin/posts GHOST_API_VERSION=v5.116.1
Claude Desktop Configuration
To use this server with Claude Desktop, you need to configure it in Claude's MCP settings:
- Open Claude Desktop
- Go to Settings > Developer > MCP Servers
- Add a new MCP Server configuration similar to:
{
"mcpServers": {
"ghost-mcp": {
"command": "/path/to/your/uv",
"args": [
"--directory",
"/path/to/your/ghost-mcp",
"run",
"mcp_server.py"
]
}
}
}
Replace /path/to/your/uv with the actual path to your uv executable and /path/to/your/ghost-mcp with the absolute path to this project directory.
Usage
Once configured, you can use the ghost_post tool from Claude to create blog posts directly in your Ghost CMS:
Create a blog post with title "My First Post" and content "Hello, world!"
The tool supports the following parameters:
- title: The title of the blog post
- content: Markdown content for the post
- author_id: ID of the author (default: "1")
- tags: List of tag names
- status: Post status (draft, published)
- feature_image: URL for the post's cover image
- code_language: Default language for code blocks
Recommend MCP Servers 💡
mcp-server-giphy
MCP Server for the Giphy API, enabling AI models to search, retrieve, and utilize GIFs from Giphy.
synergy-age-mcp
MCP (Model Context Protocol) server for SynergyAge database This server implements the Model Context Protocol (MCP) for SynergyAge, providing a standardized interface for accessing synergistic genetic intervention and aging research data. MCP enables AI assistants and agents to query comprehensive longevity datasets through structured interfaces.
@pluggedin/mcp-proxy
Plugged.in MCP Server manages all your other MCPs in one MCP.
doris-mcp-server
Doris MCP (Model Context Protocol) Server is a backend service built with Python and FastAPI. It implements the MCP, allowing clients to interact with it through defined "Tools". It's primarily designed to connect to Apache Doris databases, potentially leveraging Large Language Models (LLMs) for tasks like converting natural language queries to SQL (NL2SQL), executing queries, and performing metadata management and analysis.
cryptopanic-mcp-server
Provide latest cryptocurrency news to AI agents.
itemit-mcp
An MCP server bridging itemit asset management API with the MCP ecosystem for asset tracking