MCP server for Atlassian Confluence Data Center - access and manage content
Nothing to run from here
Ghost is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
118
downloads a day
local
runs on your machine
10
tools declared
What it does
MCP server for Ghost CMS: manage posts, pages, tags, SEO, members and newsletters via the Admin API.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'GHOST_API_URL=${GHOST_API_URL}' --env 'GHOST_ADMIN_API_KEY=${GHOST_ADMIN_API_KEY}' --transport stdio proars-ghost-mcp '--' npx -y @proars/ghost-mcp-server
# 2 — ask your agent for something these tools do
# get_site, get_settings, get_roles and 7 more
It needs GHOST_API_URL, GHOST_ADMIN_API_KEY: this reads them from your environment, so export them first.
Ghost costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
PRAll 1 server
proars1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Ghost as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads GHOST_API_URL (Ghost Admin domain, for example https://your-blog.com), GHOST_ADMIN_API_KEY (Ghost Admin API key (id:secret)) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx GHOST_API_URL …, setx GHOST_ADMIN_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'GHOST_API_URL=${GHOST_API_URL}' --env 'GHOST_ADMIN_API_KEY=${GHOST_ADMIN_API_KEY}' --transport stdio proars-ghost-mcp '--' npx -y @proars/ghost-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: GHOST_API_URL — Ghost Admin domain, for example https://your-blog.com; GHOST_ADMIN_API_KEY — Ghost Admin API key (id:secret). You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Get basic site info: title, description, logo, URL and Ghost version.
No parameter schema on file.
Get the site settings.
No parameter schema on file.
List staff roles.
No parameter schema on file.
Invite a staff user (data: email, role_id).
No parameter schema on file.
Upload one image from a local file path to Ghost storage; returns its URL.
No parameter schema on file.
Upload a theme from a local ZIP file. A theme with the same name is replaced, so this can overwrite an installed theme.
No parameter schema on file.
Activate an uploaded theme by name. This changes the live site design.
No parameter schema on file.
Shortcut to replace the tags of a post (tag names; missing tags are created). Requires id and the current updated_at. An empty list removes all tags. [PUT /admin/posts/{id}/]
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Post id. |
| updated_at | string | yes | Current updated_at value of the post, as returned by get_posts. |
| tags | array | yes | Tag names, for example ["SEO", "Ghost"]. |
Call any Ghost Admin API endpoint directly, including every route without a dedicated tool (find routes with ghost_list_endpoints). The path is relative to /ghost/api/admin, for example /labels/slug/vip/. Supports JSON bodies, multipart file uploads (files) and saving file downloads (save_to). If…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| method | string | yes | HTTP method. |
| path | string | yes | Path starting with /, relative to /ghost/api/admin, without query string. |
| query | object | no | Query parameters as a flat object, for example { limit: 20, include: 'tags' }. |
| body | object | no | JSON body for POST and PUT requests. |
| files | object | no | Multipart upload: map of form field name to absolute local file path, for example { file: '/tmp/a.png' }. Field names per route are listed by ghost_list_endpoints (upload). |
| fields | object | no | Extra multipart text fields, for example { purpose: 'image' }. Used with files. |
| save_to | string | no | Absolute path of a new file to store the response in. Use it for downloads (CSV, YAML, ZIP). Existing files are never overwritten. |
Search the catalog of all … known Ghost Admin API routes (method, path, access class, feature flag, upload fields, and the dedicated tool if there is one). Use it to find a route, then call it with its dedicated tool or with ghost_api_request. Access classes: I = allowed for Admin API integration…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| group | string | no | Resource group or first path segment, for example posts, members, stats. |
| method | string | no | HTTP method. |
| access | string | no | Access class. |
| search | string | no | Text to look for in the path, summary or handler. |
| without_dedicated_tool | boolean | no | Only list routes that have no dedicated tool (reachable via ghost_api_request). |
| offset | number | no | Number of matching routes to skip. Default 0. |
| limit | number | no | Maximum routes to return (default 50, maximum …). |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Ghost or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 2.2.1 · scanned 2 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest174731450a2567ddde4911a725925c1c0c537ae927525a0de3485237d2634a25
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (3 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| update_post_tags | no tags | |
| ghost_api_request | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| ghost_list_endpoints | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest174731450a2567dd
Scanned2026-11-02
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.2.1. Pin a release below and the command asks for exactly that one.
2.2.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Ghost can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.