# Confluence [Health: Active]

**Category:** 🏢 Workplace & Productivity  
**Repository:** https://github.com/pipeworx-io/mcp-confluence  
**GitHub Stars:** 0  
**npm Downloads (last month):** 430  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/confluence

## Description
Confluence MCP — wraps the Confluence Cloud REST API v2 (OAuth)

## Tools
Capabilities this server exposes over MCP:

- **confluence_list_pages** — List all pages in a Confluence space. Returns page ID, title, status, and version. Specify space key (e.g., "ENG", "SALES").
- **confluence_get_page** — Get full content of a Confluence page by ID. Returns title, body content, status, version, and space info.
- **confluence_search** — Search Confluence pages by keyword or CQL query. Returns matching pages with ID, title, space, and content excerpt.
- **confluence_create_page** — Create a new Confluence page with title and content. Specify parent page ID or space key (e.g., "ENG"). Returns page ID and URL.
- **confluence_list_spaces** — List all Confluence spaces in your instance. Returns space ID, key, name, type, and status. Use to discover documentation areas.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "confluence": {
    "command": "npx",
    "args": ["-y","@pipeworx/mcp-confluence"]
  }
}
```

## Documentation

## What the Confluence MCP server does

The Confluence MCP server exposes selected Confluence Cloud REST API v2 operations through the Model Context Protocol. It supports both reading existing documentation and creating new pages. Agents can discover available spaces, inspect page metadata, retrieve full page content, search across pages, and publish a new page.

This fits workflows where an AI client needs to answer questions from Confluence, locate documentation by space, summarize page content, or create a new knowledge-base entry. The integration is described as an independent, unofficial connection and is not affiliated with or endorsed by Confluence's upstream provider.

## How it works

The hosted option uses the Pipeworx gateway at `https://gateway.pipeworx.io/confluence/mcp`. The gateway connects to a Confluence account and exposes the pack's tools through MCP. Its connection also lists shared Pipeworx meta-tools, so the tool list on the hosted endpoint is larger than the five Confluence-specific tools. The gateway's `ask_pipeworx` function can route natural-language questions across the broader Pipeworx catalog.

A local option runs the npm package with `npx` and communicates over standard input and output. In local mode, the server responds to MCP initialization, tool-listing, and tool-call requests for the Confluence tools only; it does not add the gateway's shared meta-tools.

## Setup and configuration

For hosted use, sign in to Pipeworx, connect a Confluence account, and configure an MCP client with the Confluence gateway URL. Direct HTTP callers can authenticate with a Pipeworx key using a bearer token.

For local use, add an MCP server entry with the `npx -y @pipeworx/mcp-confluence` command and no gateway account. The Confluence MCP server can also be started directly with that command to verify that it launches. The README names Claude Desktop, Cursor, and Windsurf as example clients.

## Tools and capabilities

- `confluence_list_spaces` discovers spaces and returns each space's ID, key, name, type, and status.
- `confluence_list_pages` lists pages in a specified space, including IDs, titles, status, and version information.
- `confluence_get_page` retrieves a page by ID with its title, body, status, version, and space details.
- `confluence_search` finds pages using a keyword or CQL query and returns matching metadata with content excerpts.
- `confluence_create_page` creates a page with a title and content under a parent page or in a selected space, returning the new page ID and URL.

## Limitations and notes

The Confluence MCP server is focused on the operations documented above. Local mode avoids the Pipeworx gateway but is limited to this pack's tools. Hosted mode requires a connected Confluence account and Pipeworx authentication. This integration belongs to the Workplace & Productivity category.

_Full upstream README: https://allmcps.com/mcp/confluence/readme_