The Ghost connector.
Posts, pages, tags and authors. Connect once with your own key. Every agent your team runs reads the same 5 tools under one permission model.
How access is governed
5
Read tools
Open by default. They run when called, and every call is logged with the endpoint, tool and capability.
0
Write tools
Ghost exposes no write tools. Nothing it does mutates external state.
0
Destructive tools
Ghost defines no destructive tools. Nothing here deletes data.
Defaults come from the capability on each tool definition, and an admin can tighten or open any tool individually. The endpoint's capability ceiling can only tighten that policy. An endpoint scoped to read never surfaces a write tool.
Every Ghost tool
5 tools, named as the agent sees them.
- list_postsread
List published blog posts, newest first by default. Returns summaries — call get_post with a `slug` from here to read the full body. Use `filter` for Ghost NQL queries such as `tag:product` or `featured:true`.
- get_postread
Read one full post including its body. Give either `slug` (from list_posts, and what appears in the post URL) or `id`. Ask for plaintext unless you specifically need the HTML markup.
- list_pagesread
List the site's static pages (About, Pricing, Contact...) as opposed to blog posts. Same shape as list_posts.
- list_tagsread
List the publication's tags with a post count each. Use this to discover what a blog covers, then pass a tag slug to list_posts as `filter: "tag:<slug>"`.
- list_authorsread
List the publication's authors with a post count each. Use to find who writes about what, then pass an author slug to list_posts as `filter: "author:<slug>"`.
Use it from any agent
The same Ghost tools reach Claude Code, Cursor, Claude Desktop or your own agent through one MCP endpoint. The endpoint is scoped to a group, the token is issued per group and revocable from the dashboard, and an allowed-tool list and capability ceiling limit what it exposes. Reads run. Gated writes refuse unless an admin opens them. Destructive tools remain unavailable over MCP.
{
"mcpServers": {
"growth": {
"type": "http",
"url": "https://app.notara.ai/mcp/g/acme/growth",
"headers": {
"Authorization": "Bearer ntr_mcp_xxxxxxxxxxxxxxxxxxxx"
}
}
}
}The URL and token are placeholders. Real endpoints are issued per group from the dashboard.
Setup
- 01
Create a Ghost Content API Key in your Ghost account (where to find it). The key is yours: Notara stores it encrypted and never sees a bill.
- 02
Paste it into the Notara dashboard. Credentials can be scoped to the workspace or to one person.
- 03
The tools appear with their capability defaults already set. Tighten or open any of them per tool, then invite the agent to a channel or issue an MCP token.
Connect Ghost once. Use it everywhere.
Use Notara directly, or bring us the workflow that needs to be redesigned and built.