Ghost MCP Server for interacting with Ghost CMS API
Ghost MCP Server for interacting with Ghost CMS API. The ghost mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 11 defined tools rather than through you.
A Model Context Protocol (MCP) server that integrates with the Ghost Admin API. This server enables programmatic access to Ghost CMS features including post management, page management, member management, and more.
Everything the assistant can do here goes through one of these:
get_posts — Input: json { "limit": "number", // Optional: Number of posts to retrieve (1-100, default: 10) "page": "number" // Optional: Page number (default: 1)get_post — The get_post tool exposed by this serversearch_posts — Input: json { "query": "string", // Required: Search query "limit": "number" // Optional: Number of posts to retrieve (1-100, default: 10) }create_post — Input: json { "title": "string", // Required: Post title "html": "string", // Optional: HTML content "lexical": "string", // Optional: Lexicalupdate_post — Input: json { "id": "string", // Required: Post ID "title": "string", // Optional: Post title "html": "string", // Optional: HTML content "lexical"delete_post — The delete_post tool exposed by this serverget_pages — Input: json { "limit": "number", // Optional: Number of pages to retrieve (1-100, default: 10) "page": "number", // Optional: Page number (defaultget_members — Input: json { "limit": "number", // Optional: Number of members to retrieve (1-100, default: 10) "page": "number", // Optional: Page number (defaultsearch_members — Input: json { "query": "string", // Required: Search query "limit": "number", // Optional: Number of members to retrieve (1-100, default: 10)upload_image — Input: json { "file": "string", // Required: Base64 encoded image data "purpose": "string" // Optional: Image purpose (image/profile_image/icon) }Debugging — Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCPThe server ships on npm as @mtane0412/ghost-mcp-server, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
You will need 2 environment variables: GHOST_URL, GHOST_ADMIN_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Ghost's toolset — get_posts, get_post, search_posts and 8 more — is a fair guide to whether it matches your workflow. It is maintained by mtane0412; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Ghost's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| get_posts | Input: json { "limit": "number", // Optional: Number of posts to retrieve (1-100, default: 10) "page": "number" // Optional: Page number (default: 1) } |
| get_post | The get_post tool exposed by this server. |
| search_posts | Input: json { "query": "string", // Required: Search query "limit": "number" // Optional: Number of posts to retrieve (1-100, default: 10) } |
| create_post | Input: json { "title": "string", // Required: Post title "html": "string", // Optional: HTML content "lexical": "string", // Optional: Lexical content "status": "string", // Optional: Post status (published/draft/schedul |
| update_post | Input: json { "id": "string", // Required: Post ID "title": "string", // Optional: Post title "html": "string", // Optional: HTML content "lexical": "string", // Optional: Lexical content "status": "string" // Optional: |
| delete_post | The delete_post tool exposed by this server. |
| get_pages | Input: json { "limit": "number", // Optional: Number of pages to retrieve (1-100, default: 10) "page": "number", // Optional: Page number (default: 1) "order": "string", // Optional: Sort order "formats": ["string"], // |
| get_members | Input: json { "limit": "number", // Optional: Number of members to retrieve (1-100, default: 10) "page": "number", // Optional: Page number (default: 1) "order": "string", // Optional: Sort order "include": ["string"] // |
| search_members | Input: json { "query": "string", // Required: Search query "limit": "number", // Optional: Number of members to retrieve (1-100, default: 10) "include": ["string"] // Optional: Related data to include (labels/newsletters |
| upload_image | Input: json { "file": "string", // Required: Base64 encoded image data "purpose": "string" // Optional: Image purpose (image/profile_image/icon) } |
| Debugging | Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script: |
{
"mcpServers": {
"ghost-1": {
"command": "npx",
"args": ["-y", "@mtane0412/ghost-mcp-server"],
"env": {
"GHOST_URL": "your-value",
"GHOST_ADMIN_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| GHOST_URL | Endpoint or connection string the server talks to. | Yes |
| GHOST_ADMIN_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.