MCP server for Atlassian Confluence Data Center - access and manage content
Nksweb 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.
What it does
MCP server for NKS-Web CMS tenant management - manage pages, articles, news, redirects, users, and analytics via Claude Code
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user nksweb-mcp '--' npx -y @nks-hub/nksweb-mcp
# 2 — ask your agent for something these tools do
# nksweb_analytics_overview, nksweb_analytics_pages, nksweb_analytics_referrers and 46 more
Nksweb costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Nksweb 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.
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. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user nksweb-mcp '--' npx -y @nks-hub/nksweb-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
49 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.
Get aggregated traffic stats: sessions, pageviews, unique users,
No parameter schema on file.
Top visited pages ranked by visit count. Returns page path,
No parameter schema on file.
Top traffic sources ranked by visitor count. Shows referrer
No parameter schema on file.
Get breakdown by any analytics dimension. Returns ranked list
No parameter schema on file.
List blog/news articles for the current tenant. Returns id, name, url, descriptionShort, status, lang, categoryIds, and timestamps. Use this to see existing content before creating new articles.
No parameter schema on file.
Get full article details including HTML content, categories, SEO metadata, and timestamps.
No parameter schema on file.
Create a new blog article. Requires name and url (slug). Use descriptionShort for listing excerpts and description for full HTML content. Link to categories via categoryIds array. Set status=1 to publish.
No parameter schema on file.
Update an existing article. Only send fields to change — omitted fields keep their current values. Use to publish drafts, update content, or reassign categories.
No parameter schema on file.
Permanently delete an article. Soft-deleted — won
No parameter schema on file.
List article categories. Categories use a nested tree structure — root categories have parent=null, subcategories reference their parent
No parameter schema on file.
Get category details including title, description, and parent category reference.
No parameter schema on file.
Create a new article category. Set parentId to nest under an existing category, or omit for a root-level category.
No parameter schema on file.
Update a category
No parameter schema on file.
Delete a category. Articles assigned to this category will lose the association.
No parameter schema on file.
List uploaded files/media assets. Returns id, name, fileName (stored name), mimeType, fileSize, and timestamps. Files are images, documents, or other media uploaded through the CMS admin.
No parameter schema on file.
Get file metadata by ID including original name, stored filename, MIME type, file size in bytes, and upload timestamp.
No parameter schema on file.
Permanently delete a file and its physical storage. This removes the file from disk — any pages or articles referencing it will have broken links. Cannot be undone.
No parameter schema on file.
List contact form submissions received from website visitors. Returns id, name, email, phone, subject, message body, isRead flag, and timestamps. Messages are sorted newest first. Use to monitor incoming inquiries.
No parameter schema on file.
Get full details of a contact message including sender name, email, phone, subject, message body, IP address, read status, and timestamps.
No parameter schema on file.
Mark a contact message as read or unread. Defaults to marking as read. Use to track which messages have been reviewed by an admin.
No parameter schema on file.
Permanently delete a contact message. Cannot be undone.
No parameter schema on file.
List news/announcement items for the current tenant. Returns id, name, url, published status, and timestamps. News items are time-based content like announcements, updates, or press releases.
No parameter schema on file.
Get full details of a news item by ID including HTML content and publication status.
No parameter schema on file.
Create a new news item. Requires name and url (slug). Set published=true to make it visible on the website immediately.
No parameter schema on file.
Update a news item. Only send fields to change. Use to publish/unpublish (published flag) or update content.
No parameter schema on file.
Permanently delete a news item by ID. This action cannot be undone.
No parameter schema on file.
List CMS pages for the current tenant. Supports filtering by type, status, search term (matches name, url, content), and language. Returns id, name, url, content, type, status, SEO fields, and navigation flags.
No parameter schema on file.
Get full details of a single page by ID including HTML content, SEO metadata, navigation settings, and timestamps.
No parameter schema on file.
Create a new CMS page. Requires name and url (slug). The page type determines the template used for rendering. Set status=1 to publish, status=0 for draft. Navigation flags control where the page appears in menus.
No parameter schema on file.
Update an existing page. Only send fields you want to change — omitted fields keep their current values. Use this to publish drafts (status=1), update content, or change navigation placement.
No parameter schema on file.
List all content blocks for a page. Content blocks are named text sections stored in extraData.content_blocks, editable via Quill editors in admin. Returns key, label, and HTML content for each block.
No parameter schema on file.
Create or update a single content block on a page. Content blocks are named text sections (e.g.
No parameter schema on file.
Delete a single content block from a page by key. The template will fall back to its hardcoded default text. Preserves all other blocks and extraData keys.
No parameter schema on file.
Permanently delete a page by ID. This uses soft-delete — the page may still exist in the database but won
No parameter schema on file.
List URL redirect rules for the current tenant. Returns oldUrl, newUrl, statusCode, active flag, hitCount, and timestamps. Redirects handle moved/renamed pages to prevent broken links and preserve SEO.
No parameter schema on file.
Get redirect rule details including hit count (how many times it was triggered) and last hit timestamp.
No parameter schema on file.
Create a URL redirect rule. When a visitor hits oldUrl, they are redirected to newUrl with the specified HTTP status code. Use 301 for permanent moves (SEO-friendly), 302 for temporary, 307 for temporary with method preservation.
No parameter schema on file.
Update a redirect rule. Use to change target URL, switch status code, enable/disable, or update notes.
No parameter schema on file.
Delete a redirect rule. The old URL will return 404 after deletion.
No parameter schema on file.
List all tenant settings as key-value pairs. Returns configuration like site name, contact info, social links, analytics IDs, theme settings, and feature flags. Settings control the tenant
No parameter schema on file.
Get a specific setting value by its key. Common keys include: site_name, site_description, contact_email, contact_phone, address_*, rybbit_enabled, rybbit_site_id, social media URLs.
No parameter schema on file.
Update one or more settings at once. Pass a JSON object with key-value pairs. Only specified keys are updated — others remain unchanged. Use to configure site metadata, contact info, or feature flags.
No parameter schema on file.
List available tenants. With a multi-tenant API key returns all active tenants.
No parameter schema on file.
Switch the active tenant context for all subsequent MCP operations.
No parameter schema on file.
List admin users for the current tenant. Returns id, name, username, and role. Sensitive fields (password, tokens) are excluded from the response.
No parameter schema on file.
Get user profile by ID. Returns name, username, role, and timestamps. Password and security tokens are never exposed.
No parameter schema on file.
Create a new admin user. Requires username (must be unique) and password. Role determines access level: 0=Admin (full access), 1=Moderator (limited access).
No parameter schema on file.
Update a user
No parameter schema on file.
Permanently delete a user account. The user will lose access immediately. Cannot be undone.
No parameter schema on file.
- 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 Nksweb or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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 |
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.
Tools were statically extracted from the published source (49 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| nksweb_analytics_overview | no tags | |
| nksweb_analytics_pages | no tags | |
| nksweb_analytics_referrers | no tags | |
| nksweb_analytics_metric | no tags | |
| nksweb_list_articles | no tags | |
| nksweb_get_article | no tags | |
| nksweb_create_article | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( client.post("/articles") at build/tools/articles.js:81 |
| nksweb_update_article | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( client.put(/articles/${id}) at build/tools/articles.js:118 |
| nksweb_delete_article | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP DELETE ( client.delete(/articles/${args.id}) at build/tools/articles.js:145 |
| nksweb_list_categories | no tags | |
| nksweb_get_category | no tags | |
| nksweb_create_category | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( client.post("/categories") at build/tools/categories.js:75 |
| nksweb_update_category | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( client.put(/categories/${id}) at build/tools/categories.js:106 |
| nksweb_delete_category | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP DELETE ( client.delete(/categories/${args.id}) at build/tools/categories.js:133 |
| nksweb_list_files | sensitive-source | sensitive-source: keyword "list_files" |
| nksweb_get_file | no tags | |
| nksweb_delete_file | file-writestate-writeexternal-sink | file-write: keyword "delete_file" in tool name; state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP DELETE ( client.delete(/files/${args.id}) at build/tools/files.js:73 |
| nksweb_list_messages | no tags | |
| nksweb_get_message | no tags | |
| nksweb_mark_message_read | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PATCH ( client.patch(/messages/${id}/read) at build/tools/messages.js:75 |
| nksweb_delete_message | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP DELETE ( client.delete(/messages/${args.id}) at build/tools/messages.js:102 |
| nksweb_list_news | no tags | |
| nksweb_get_news_item | no tags | |
| nksweb_create_news | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( client.post("/news") at build/tools/news.js:76 |
| nksweb_update_news | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( client.put(/news/${id}) at build/tools/news.js:108 |
| nksweb_delete_news | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP DELETE ( client.delete(/news/${args.id}) at build/tools/news.js:135 |
| nksweb_list_pages | no tags | |
| nksweb_get_page | untrusted-input | untrusted-input: keyword "get_page" |
| nksweb_create_page | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( client.post("/pages") at build/tools/pages.js:117 |
| nksweb_update_page | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( client.put(/pages/${id}) at build/tools/pages.js:158 |
| nksweb_list_content_blocks | no tags | |
| nksweb_upsert_content_block | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( client.put(/pages/${args.pageId}) at build/tools/pages.js:248 |
| nksweb_delete_content_block | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP PUT ( client.put(/pages/${args.pageId}) at build/tools/pages.js:301 |
| nksweb_delete_page | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP DELETE ( client.delete(/pages/${args.id}) at build/tools/pages.js:335 |
| nksweb_list_redirects | no tags | |
| nksweb_get_redirect | no tags | |
| nksweb_create_redirect | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( client.post("/redirects") at build/tools/redirects.js:77 |
| nksweb_update_redirect | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( client.put(/redirects/${id}) at build/tools/redirects.js:110 |
| nksweb_delete_redirect | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP DELETE ( client.delete(/redirects/${args.id}) at build/tools/redirects.js:137 |
| nksweb_list_settings | no tags | |
| nksweb_get_setting | no tags | |
| nksweb_update_settings | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( client.put("/settings") at build/tools/settings.js:70 |
| nksweb_list_tenants | no tags | |
| nksweb_set_tenant | state-write | state-write: declares readOnlyHint: false |
| nksweb_list_users | no tags | |
| nksweb_get_user | no tags | |
| nksweb_create_user | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( client.post("/users") at build/tools/users.js:76 |
| nksweb_update_user | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( client.put(/users/${id}) at build/tools/users.js:108 |
| nksweb_delete_user | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP DELETE ( client.delete(/users/${args.id}) at build/tools/users.js:135 |
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.
Supply chain and provenance
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 0.2.3. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
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.
Any signed-in account that does not publish Nksweb can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.