Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content
Nothing to run from here
Castor 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.
100/100
trust score
5
downloads a day
local
runs on your machine
334
downloads in 30d
What it does
Castor for Confluence Data Center — MCP server bridging Confluence DC with AI agents
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'CONFLUENCE_URL=${CONFLUENCE_URL}' --env 'CONFLUENCE_USER_TOKEN=${CONFLUENCE_USER_TOKEN}' --transport stdio castor-mcp '--' npx -y castor-mcp
# 2 — ask your agent for something these tools do
# list_spaces, get_space, get_page and 77 more
It needs CONFLUENCE_URL, CONFLUENCE_USER_TOKEN: this reads them from your environment, so export them first.
Castor costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MOAll 2 servers
moosejudge2 servers
2 categories
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 Castor 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 CONFLUENCE_URL (Base URL of the Confluence Data Center instance), CONFLUENCE_USER_TOKEN (Personal Access Token for standard operations) 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 CONFLUENCE_URL …, setx CONFLUENCE_USER_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'CONFLUENCE_URL=${CONFLUENCE_URL}' --env 'CONFLUENCE_USER_TOKEN=${CONFLUENCE_USER_TOKEN}' --transport stdio castor-mcp '--' npx -y castor-mcpReconnect, 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: CONFLUENCE_URL — Base URL of the Confluence Data Center instance; CONFLUENCE_USER_TOKEN — Personal Access Token for standard operations. 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
80 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.
List Confluence spaces, optionally filtered by type (global or personal).
No parameter schema on file.
Get a single Confluence space by key.
No parameter schema on file.
Get a single Confluence page by ID, including its body (storage format HTML) and current
No parameter schema on file.
Create a new Confluence page in a space. Body must be storage-format HTML.
No parameter schema on file.
Update a Confluence page
No parameter schema on file.
Search Confluence content using CQL (preferred over any other search mechanism).
No parameter schema on file.
Get all permission grants (user/group/anonymous) on a Confluence space. Requires space-admin
No parameter schema on file.
List Confluence content (pages, blog posts, etc.) with optional filters. Broader than
No parameter schema on file.
Delete a Confluence page. Omit status to trash a current page; to permanently purge an
No parameter schema on file.
Get a page
No parameter schema on file.
Get a macro
No parameter schema on file.
Get a macro
No parameter schema on file.
List all custom properties (key/value metadata) stored on a page.
No parameter schema on file.
Get a single custom property by key from a page.
No parameter schema on file.
Create a custom property (key/value metadata) on a page. Fails if the key already exists — use update_page_property instead.
No parameter schema on file.
Update an existing page property
No parameter schema on file.
Delete a custom property from a page.
No parameter schema on file.
Permanently delete one historical version of a page (not the current version).
No parameter schema on file.
Scan all content in a space via cursor-based pagination — for bulk/migration-style traversal,
No parameter schema on file.
Convert content body between representations, e.g.
No parameter schema on file.
List users watching a page.
No parameter schema on file.
List a page
No parameter schema on file.
List a page\
No parameter schema on file.
List a page
No parameter schema on file.
List the content types that have descendants under this page (e.g. \
No parameter schema on file.
List all of a page
No parameter schema on file.
Count how many descendant pages a page has.
No parameter schema on file.
Replace a page
No parameter schema on file.
Get all of a page
No parameter schema on file.
Get a page\
No parameter schema on file.
Get a page
No parameter schema on file.
Publish an in-progress blueprint draft (legacy editor) as a real page. The draftId comes
No parameter schema on file.
Publish an in-progress blueprint draft (shared/collaborative editor) as a real page. The
No parameter schema on file.
List labels on a page.
No parameter schema on file.
Add one or more labels to a page.
No parameter schema on file.
Remove a label from a page.
No parameter schema on file.
Get labels commonly used together with a given label, globally (returns global labels only).
No parameter schema on file.
Search labels by name, namespace, space, or owner.
No parameter schema on file.
Get the most popular labels instance-wide.
No parameter schema on file.
Get recently used labels instance-wide.
No parameter schema on file.
List all labels used anywhere in a space.
No parameter schema on file.
Get labels commonly used together with a given label, within one space.
No parameter schema on file.
Get the most popular labels within a space.
No parameter schema on file.
Get recently used labels within a space.
No parameter schema on file.
Get a page
No parameter schema on file.
Permanently delete multiple pages in one request. DESTRUCTIVE and irreversible for pages
No parameter schema on file.
Count how many descendants each of the given pages has that would be deleted alongside it.
No parameter schema on file.
Get the instance
No parameter schema on file.
Preview the effect of a bulk_delete_pages call without deleting anything — same input shape.
No parameter schema on file.
Get a space
No parameter schema on file.
List a page
No parameter schema on file.
Upload a new attachment to a page. Content must be base64-encoded.
No parameter schema on file.
Permanently delete an attachment (all versions).
No parameter schema on file.
Rename an attachment (update its title). Call list_page_attachments first to obtain currentVersion.
No parameter schema on file.
Upload new binary content for an existing attachment, creating a new version. Content must
No parameter schema on file.
Get Confluence
No parameter schema on file.
Rename an attachment
No parameter schema on file.
Permanently delete one historical version of an attachment (not the current version).
No parameter schema on file.
Create a new global Confluence space. See skill://spaces-admin for real gotchas across this tool surface.
No parameter schema on file.
Create a new private space (visible only to its creator until permissions are granted).
No parameter schema on file.
Create the personal space for the acting user (one per user, key derived automatically).
No parameter schema on file.
Permanently delete a space and all its content. DESTRUCTIVE, asynchronous, and irreversible.
No parameter schema on file.
Update a space
No parameter schema on file.
Archive a space, making it read-only and hidden from default space listings.
No parameter schema on file.
Add a category label to a space.
No parameter schema on file.
Remove a category label from a space.
No parameter schema on file.
Get a space
No parameter schema on file.
List a space\
No parameter schema on file.
List all custom properties (key/value metadata) stored on a space.
No parameter schema on file.
Create a custom property on a space. Fails if the key already exists — use update_space_property instead.
No parameter schema on file.
Get a single custom property by key from a space.
No parameter schema on file.
Update an existing space property
No parameter schema on file.
Delete a custom property from a space.
No parameter schema on file.
Restore a previously deleted space, if still within the recovery window. Admin operation.
No parameter schema on file.
Permanently delete all trashed content in a space in one operation. DESTRUCTIVE, asynchronous, and irreversible.
No parameter schema on file.
List a space
No parameter schema on file.
List users watching a space.
No parameter schema on file.
List all global permission grants instance-wide. See skill://permissions for real gotchas across this tool surface.
No parameter schema on file.
Replace global permissions for multiple users/groups in one call.
No parameter schema on file.
Get global permissions granted to anonymous (unauthenticated) users.
No parameter schema on file.
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 Castor 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 100 / 100
Release 0.6.2 · scanned 14 Oct 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 score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digestd4e948ab3a55620d34f9a55769de31ce9c8a6d95d1344d929e7e5185eeee5de4
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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 digestd4e948ab3a55620d
Scanned2026-10-14
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 0.6.2. Pin a release below and the command asks for exactly that one.
0.6.2
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 Castor 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.